{ "complete": true, "report": { "bucket": "emo_Pleasure_Ecstasy", "label": "Intense Pleasure Ecstasy", "definition": { "id": "emo_Pleasure_Ecstasy", "category": "emotion", "head": "emo_Pleasure_Ecstasy", "pole": "high", "label": "Intense Pleasure Ecstasy", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_pleasure_ecstasy/full-v2-sealed/sealed-selected", "mission": "emotion_pleasure_ecstasy", "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": 6.283172998428345, "genuineness": 4.262079477310181, "wer": 0.018662097385331533, "identity": 0.5505906672775746, "voiceclap": -0.13120991886593403, "fitness": 0.6187813514492989, "steering_v2": 0.5898710327642298, "raw_target": 0.5665340752899647, "target_cdf": 0.5898710327642298, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 0.99, "by_arm": { "reference": { "n": 50, "ce": 6.295047311782837, "genuineness": 4.255928997993469, "wer": 0.018198359257730782, "identity": 0.5505906672775746, "fitness": 0.6264950853701835, "steering_v2": 0.6055267315853459 }, "none": { "n": 50, "ce": 6.271298685073853, "genuineness": 4.268229956626892, "wer": 0.019125835512932288, "identity": null, "fitness": 0.6110676175284143, "steering_v2": 0.5742153339431139 } } } } ], "selected_wording": { "id": "manual-1c5ef4ec2662", "general": "Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.", "inline": [ "Begin with a breathy intake that immediately suggests an upward rush of sensation.", "Allow the mid-range of the voice to bloom with effortless, sustained resonance.", "Let the final articulation dissolve into a warm, audible exhalation of pure delight." ], "cfg": 3, "recipe": "P04", "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": 2.0 }, "n": 20, "target_z": 1.0074462877086792, "target_raw": 1.0194116726517677, "ce": 6.218996191024781, "genuineness": 4.255050313472748, "identity": 0.5433235123753548, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.047520081698894504, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 0.6183837901493703, "target_raw": 0.7818771995604038, "ce": 6.182261300086975, "genuineness": 4.222728705406189, "identity": 0.542235815525055, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.04860777854919433, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 1.0074462877086792, "target_raw": 1.0194116726517677, "ce": 6.218996191024781, "genuineness": 4.255050313472748, "identity": 0.5433235123753548, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.047520081698894504, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 2.1400390803475546, "target_raw": 1.710893976688385, "ce": 6.042271733283997, "genuineness": 4.153064668178558, "identity": 0.3867581933736801, "wer": 0.023684210526315787, "valid_fraction": 0.95, "identity_delta": -0.20408540070056916, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 1.729687493898272, "target_raw": 1.4603618681430817, "ce": 6.168361663818359, "genuineness": 4.185072386264801, "identity": 0.43084029871970414, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.1600032953545451, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 1.4900878856292101, "target_raw": 1.3140790291130542, "ce": 6.164390301704406, "genuineness": 4.181306850910187, "identity": 0.48110154941678046, "wer": 0.008333333333333333, "valid_fraction": 1, "identity_delta": -0.1097420446574688, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 1.130664063262716, "target_raw": 1.0946398675441742, "ce": 6.245008444786071, "genuineness": 4.272309470176697, "identity": 0.49773415848612784, "wer": 0.011019736842105263, "valid_fraction": 0.95, "identity_delta": -0.09310943558812142, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 0.6741211046568388, "target_raw": 0.815906523168087, "ce": 6.230711627006531, "genuineness": 4.30023775100708, "identity": 0.5207124173641204, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.07013117671012878, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 0.5281250134238016, "target_raw": 0.7267714746296405, "ce": 6.210060691833496, "genuineness": 4.322203922271728, "identity": 0.5155949980020523, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.07524859607219696, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": 0.3220520099092063, "target_raw": 0.6009576462209225, "ce": 6.211252069473266, "genuineness": 4.305886232852936, "identity": 0.49746800735592844, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.09337558671832084, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 0.6183837901493703, "target_raw": 0.7818771995604038, "ce": 6.182261300086975, "genuineness": 4.222728705406189, "identity": 0.542235815525055, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.04860777854919433, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 0.558807384311237, "target_raw": 0.745503994077444, "ce": 6.237860012054443, "genuineness": 4.307769060134888, "identity": 0.5523445501923561, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.03849904388189316, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 0.4286865298252465, "target_raw": 0.6660612598061562, "ce": 6.212840580940247, "genuineness": 4.283135604858399, "identity": 0.5510676309466362, "wer": 0.012569444444444444, "valid_fraction": 1, "identity_delta": -0.03977596312761307, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 2.189843746949136, "target_raw": 1.7413012385368347, "ce": 6.020032191276551, "genuineness": 4.173147964477539, "identity": 0.31866631135344503, "wer": 0.019060672514619882, "valid_fraction": 1, "identity_delta": -0.2721772827208042, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 2.0017578053304694, "target_raw": 1.6264690577983856, "ce": 6.031350541114807, "genuineness": 4.159026944637299, "identity": 0.4201695442199707, "wer": 0.009236111111111112, "valid_fraction": 1, "identity_delta": -0.17067404985427856, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 1.9492187689153568, "target_raw": 1.5943923801183701, "ce": 6.110380101203918, "genuineness": 4.175972199440002, "identity": 0.39012405201792716, "wer": 0.02227704678362573, "valid_fraction": 0.95, "identity_delta": -0.2007195420563221, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 1.8871093380845456, "target_raw": 1.556472685933113, "ce": 6.1439379215240475, "genuineness": 4.150554251670838, "identity": 0.4565277950838208, "wer": 0.005756578947368421, "valid_fraction": 1, "identity_delta": -0.13431579899042845, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 1.7762695694620716, "target_raw": 1.4888016402721405, "ce": 6.131428217887878, "genuineness": 4.229946088790894, "identity": 0.4779144424945116, "wer": 0.012916666666666667, "valid_fraction": 1, "identity_delta": -0.11292915157973767, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 1.7437500341696768, "target_raw": 1.4689474761486054, "ce": 6.081190776824951, "genuineness": 4.22994612455368, "identity": 0.4320790311321616, "wer": 0.014232886136910905, "valid_fraction": 0.95, "identity_delta": -0.15876456294208766, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 1.4748046763643463, "target_raw": 1.3047481656074524, "ce": 6.212046337127686, "genuineness": 4.236535978317261, "identity": 0.43287375159561636, "wer": 0.011165935672514619, "valid_fraction": 1, "identity_delta": -0.15796984247863294, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 1.4533691496631846, "target_raw": 1.291661125421524, "ce": 6.170744490623474, "genuineness": 4.149612832069397, "identity": 0.4990378566086292, "wer": 0.008680555555555556, "valid_fraction": 1, "identity_delta": -0.09180573746562004, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 1.4015625158644929, "target_raw": 1.2600316017866136, "ce": 6.176502895355225, "genuineness": 4.1841310381889345, "identity": 0.42693652808666227, "wer": 0.023288398692810457, "valid_fraction": 0.95, "identity_delta": -0.16390706598758698, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 1.3126953138728887, "target_raw": 1.2057754755020142, "ce": 6.242625641822815, "genuineness": 4.229318559169769, "identity": 0.5168325655162335, "wer": 0.008596491228070175, "valid_fraction": 1, "identity_delta": -0.07401102855801582, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 1.188201903739139, "target_raw": 1.129768466949463, "ce": 6.224357485771179, "genuineness": 4.225552892684936, "identity": 0.49049644097685813, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.10034715309739113, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 1.159130882065801, "target_raw": 1.1120197251439095, "ce": 6.172928667068481, "genuineness": 4.239987754821778, "identity": 0.4992153912782669, "wer": 0.00804093567251462, "valid_fraction": 1, "identity_delta": -0.09162820279598236, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 1.0338043224641218, "target_raw": 1.0355040535330773, "ce": 6.185239839553833, "genuineness": 4.294903099536896, "identity": 0.49259276799857615, "wer": 0.01608187134502924, "valid_fraction": 0.95, "identity_delta": -0.0982508260756731, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 1.0200317509518695, "target_raw": 1.0270954802632333, "ce": 6.190998268127442, "genuineness": 4.210176634788513, "identity": 0.4639600418508053, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.126883552223444, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 0.9184326296007029, "target_raw": 0.9650661304593087, "ce": 6.219194722175598, "genuineness": 4.25599172115326, "identity": 0.4865300789475441, "wer": 0.01152046783625731, "valid_fraction": 1, "identity_delta": -0.10431351512670517, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 0.674694837938104, "target_raw": 0.8162568047642708, "ce": 6.186431217193603, "genuineness": 4.255991697311401, "identity": 0.5398046895861626, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.0510389044880867, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 0.6579590012691594, "target_raw": 0.8060390681028367, "ce": 6.195366764068604, "genuineness": 4.249088108539581, "identity": 0.5089355543255806, "wer": 0.006666666666666666, "valid_fraction": 1, "identity_delta": -0.08190803974866867, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 0.6101562506101728, "target_raw": 0.7768540367484092, "ce": 6.251759696006775, "genuineness": 4.307455205917359, "identity": 0.5200057789683342, "wer": 0.003125, "valid_fraction": 1, "identity_delta": -0.07083781510591507, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 0.38741150053695206, "target_raw": 0.6408616006374359, "ce": 6.235477232933045, "genuineness": 4.293020343780517, "identity": 0.4930480673909187, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.09779552668333054, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 0.28735352191740704, "target_raw": 0.5797731652855873, "ce": 6.195763874053955, "genuineness": 4.296158397197724, "identity": 0.5152905814349651, "wer": 0.00625, "valid_fraction": 1, "identity_delta": -0.07555301263928413, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 0.28262938592209313, "target_raw": 0.5768889367580414, "ce": 6.219790434837341, "genuineness": 4.3105932712554935, "identity": 0.5299749739468098, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.0608686201274395, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": -0.027197271307234212, "target_raw": 0.3877303510904312, "ce": 6.197352433204651, "genuineness": 4.363625776767731, "identity": 0.5908435940742492, "wer": 0.006666666666666666, "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": -0.1536865164014449, "target_raw": 0.31050482466816903, "ce": 6.196160984039307, "genuineness": 4.334756016731262, "identity": 0.5723303556442261, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.018513238430023192, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": -0.16787109855511081, "target_raw": 0.30184470638632777, "ce": 6.232300162315369, "genuineness": 4.350132310390473, "identity": 0.5773262470960617, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.013517346978187562, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": -0.20352783852386996, "target_raw": 0.2800751835107803, "ce": 6.244611310958862, "genuineness": 4.333187007904053, "identity": 0.5654207214713096, "wer": 0.007894736842105263, "valid_fraction": 0.95, "identity_delta": -0.025422872602939607, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.3608984345406619, "target_raw": 0.18399565428495407, "ce": 6.2631177234649655, "genuineness": 4.354964876174927, "identity": 0.5997853672504425, "wer": 0.0058095238095238096, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 0.5285815317777994, "target_raw": 0.7270501929521561, "ce": 6.267406778335571, "genuineness": 4.337140951156616, "identity": 0.5559286171197891, "wer": 0.01825098814229249, "valid_fraction": 0.98, "identity_delta": -0.043856750130653384, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 0.31316406277457776, "target_raw": 0.5955312845110893, "ce": 6.290758256912231, "genuineness": 4.35370964050293, "identity": 0.5600521922111511, "wer": 0.00823640127987954, "valid_fraction": 1, "identity_delta": -0.039733175039291385, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 0.2628234887240066, "target_raw": 0.564796834886074, "ce": 6.274078598022461, "genuineness": 4.385215377807617, "identity": 0.528790972828865, "wer": 0.011014492753623187, "valid_fraction": 1, "identity_delta": -0.07099439442157746, "identity_pairs": 50, "gates_pass": false, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": 0.05034057405057112, "ci95_z": [ -0.04686033974421556, 0.16163207751635264 ], "language_deltas": { "en": -0.025683576588889968, "de": 0.0042724348335448515, "fr": -0.09360349018842135, "nl": 0.23356323098701554, "es": 0.13315427120960655 }, "languages_improved": 3, "clear_gain": false, "delta_ce": 0.016679658889770507, "delta_genuineness": -0.0315057373046875, "delta_wer": -0.0027780914737436475, "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": -0.2154174690032217, "ci95_z": [ -0.2857397349409353, -0.16663084057405056 ], "language_deltas": { "en": -0.18159177975202576, "de": -0.2000976471736796, "fr": -0.14418943180708776, "nl": -0.20325928194864787, "es": -0.3479492043346676 }, "languages_improved": 0, "clear_gain": false, "delta_ce": 0.023351478576660156, "delta_genuineness": 0.016568689346313475, "delta_wer": -0.010014586862412949, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.8894799663184614, "ci95_z": [ 0.7711132685736601, 1.0720947080933318 ], "language_deltas": { "en": 0.7544433417943962, "de": 0.7858642438738651, "fr": 0.8870117079957044, "nl": 0.7804077077028214, "es": 1.2396728302255198 }, "languages_improved": 5, "clear_gain": true, "delta_ce": 0.004289054870605468, "delta_genuineness": -0.01782392501831055, "delta_wer": 0.01244146433276868, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 2.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793034263.859554, "example": { "text": "La route tourne à gauche après le pont. Continue... jusqu’à la petite barrière en bois. Je t’attendrai de l’autre côté.", "sentences": [ "La route tourne à gauche après le pont.", "Continue... jusqu’à la petite barrière en bois.", "Je t’attendrai de l’autre côté." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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.", "language": "fr", "seed": 1701, "scale": 0.0, "cfg": 2.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "0023fa918952e0f4fee813cef3d32e9b335ea3b21e237ea47e2c5df690e53a58", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "d4efc76ec48bdae2096f119e6ed2a82f8d8bea54ca2d1139e95c1923dcc06298", "generation_seconds_batch": 21.397837052936666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8932363986968994, "target_z": 0.80078126525432, "ce": 6.252951145172119, "genuineness": 3.9425034523010254, "identity": 0.12055042386054993, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in.", "wer": 0.1111111111111111, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/0023fa918952e0f4fee813cef3d32e9b335ea3b21e237ea47e2c5df690e53a58.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "019dd1739035d589ec451fa6b2989b3c1de0d18fc8c158cffed3c5c57e982e74", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1e78d1d3a4a142c6ab844eec9764048afb35eabda3d6a98ab984f811ea562104", "generation_seconds_batch": 22.57671688706614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9337794780731201, "target_z": 0.8671875915259202, "ce": 6.0146708488464355, "genuineness": 4.2249250411987305, "identity": 0.3403712213039398, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/019dd1739035d589ec451fa6b2989b3c1de0d18fc8c158cffed3c5c57e982e74.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "7eae36c99e264de7725ceb1744486fe5f1cc9562b71c5870bf4f84043ca54cf5", "generation_seconds_batch": 15.201710833003744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19088797271251678, "target_z": -0.34960936737284, "ce": 6.133810997009277, "genuineness": 4.545003414154053, "identity": 0.728285551071167, "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_Pleasure_Ecstasy/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "02eaca50ce07060c478c06258b34ecb8da8c39fe22cbc42356a3cb68c59ae1ba", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "905a8c171748fe03df8db1a43f84de056da22d7a525a160e488d98992349ac07", "generation_seconds_batch": 21.02013487892691, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6253958940505981, "target_z": 2.000000048813824, "ce": 6.109982967376709, "genuineness": 4.419482707977295, "identity": 0.571491539478302, "hypothesis": "J'ai trouvé la 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_Pleasure_Ecstasy/02eaca50ce07060c478c06258b34ecb8da8c39fe22cbc42356a3cb68c59ae1ba.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": "03011e41ec59e4d53e8568f9becd5d9ba9c2d8f6a642f6c8308e31d27f2dd446", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2e8d382d70d2b875a2705410f61357bd2f7d52c41201b0b3c5b566d2c11e486", "generation_seconds_batch": 15.985609538038261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8693875074386597, "target_z": 0.7617186859318559, "ce": 6.284721851348877, "genuineness": 4.432034492492676, "identity": 0.6067174077033997, "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_Pleasure_Ecstasy/03011e41ec59e4d53e8568f9becd5d9ba9c2d8f6a642f6c8308e31d27f2dd446.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "035e8d81d77103f0ff19b1699256553e836ae4516c6cd1624850d32a3f4e9f07", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "71c6d45c0c927903d64795840c9f4f43147d7005c6f7ff941609e971189960bd", "generation_seconds_batch": 24.15872675809078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7303308248519897, "target_z": 2.171875085424192, "ce": 6.332377910614014, "genuineness": 4.250029563903809, "identity": 0.5032765865325928, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/035e8d81d77103f0ff19b1699256553e836ae4516c6cd1624850d32a3f4e9f07.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": "036b23681b322e45ffdb11abccd9e48c37e5a3a0c43c4f0c93c28131857381ab", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8e17b5a86c37fee2d623c76e2d6d6bed3f5b5ec1f3ee18e89605d9553e70a8ae", "generation_seconds_batch": 20.68835086992476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7000607252120972, "target_z": 0.4843749389827199, "ce": 6.300607204437256, "genuineness": 4.268857479095459, "identity": 0.7017318606376648, "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_Pleasure_Ecstasy/036b23681b322e45ffdb11abccd9e48c37e5a3a0c43c4f0c93c28131857381ab.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": "03a6681c83d05623b873deb0bcc13adcd8156f98758c1ec6a9e17bc584fc2c79", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9dfad69501634d33f8fd7f4667f2f639002ffaf11288515f8b62de547d1fcfd9", "generation_seconds_batch": 16.048848994076252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027523398399353027, "target_z": -0.617187493898272, "ce": 6.09409761428833, "genuineness": 3.9425034523010254, "identity": 0.5217846632003784, "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_Pleasure_Ecstasy/03a6681c83d05623b873deb0bcc13adcd8156f98758c1ec6a9e17bc584fc2c79.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "03bf160bbe0f27a303e3759d807b763afb9dcb0d05b66d1055e36340a58011d2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4e306e13f0c50e58fdb06813340ca14a49fe8b56fd33300af83270f76daf4329", "generation_seconds_batch": 17.62034638703335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5414659380912781, "target_z": 0.22460934296592794, "ce": 6.141753673553467, "genuineness": 4.545003414154053, "identity": 0.7442339658737183, "hypothesis": "La porte 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_Pleasure_Ecstasy/03bf160bbe0f27a303e3759d807b763afb9dcb0d05b66d1055e36340a58011d2.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "03c601916cce95fa8a4c2c112fe573c678e0a65bc4a7f44c075558b339e0fe5b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b9075c9f4c075941fe8ba47f3525242c7a6cf99ee9f2882c1591ab68274ef7a8", "generation_seconds_batch": 23.423947582952678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0959515571594238, "target_z": 1.132812506101728, "ce": 6.260893821716309, "genuineness": 4.519899368286133, "identity": 0.6617786884307861, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/03c601916cce95fa8a4c2c112fe573c678e0a65bc4a7f44c075558b339e0fe5b.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "04168a802389656552b832bc77f9860cdcbb1f4e0d9c531e2bba9f22e8230588", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3cc2912aa841c3a371aaeeeb78908348245e66f2ad26f821e7709044d9b7d3ed", "generation_seconds_batch": 17.0840971339494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1579585075378418, "target_z": 1.2343749389827199, "ce": 6.41180419921875, "genuineness": 4.607763767242432, "identity": 0.6416707038879395, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/04168a802389656552b832bc77f9860cdcbb1f4e0d9c531e2bba9f22e8230588.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "05453674fe0074579735bf812a1db51126ccee9337bd240e450b635435c2c35e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "71f89df274e1ca3934e5e981fa7fb8a6a0e58ede13b0ef90f3350fcc0e35efc2", "generation_seconds_batch": 16.906033062026836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4839541912078857, "target_z": 3.406249975593088, "ce": 5.764476776123047, "genuineness": 3.8295347690582275, "identity": 0.42897555232048035, "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_Pleasure_Ecstasy/05453674fe0074579735bf812a1db51126ccee9337bd240e450b635435c2c35e.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "055f1d6908591c433c8c7e8c4dd945de9aa146b633f905dcd1c547c1d2fcc2f8", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6f7203e1277e7fde2b48f687c5e140e6e420e44a5b19f4d79faef4c10af67a9b", "generation_seconds_batch": 21.820775259984657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4489144086837769, "target_z": 1.71093746949136, "ce": 6.205295085906982, "genuineness": 4.011539936065674, "identity": 0.18649151921272278, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/055f1d6908591c433c8c7e8c4dd945de9aa146b633f905dcd1c547c1d2fcc2f8.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "0333965dfbeea4ff7de4a3c1b911decdcb43df1c1cdf694ab74996908de90dab", "generation_seconds_batch": 15.879963418934494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42475569248199463, "target_z": 0.03344728106999902, "ce": 6.475345611572266, "genuineness": 4.469690799713135, "identity": 0.6292300820350647, "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_Pleasure_Ecstasy/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "05e878953d6303c23412356937d973e6498ab315e8c3eb1ea670699be3553f15", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0827880fade80896b7ab5c852b0f582cf8de468635ed56a2b39f3b5f2e143c80", "generation_seconds_batch": 19.704209515010007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.415526032447815, "target_z": 1.656249975593088, "ce": 6.157639026641846, "genuineness": 4.570107460021973, "identity": 0.490647554397583, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/05e878953d6303c23412356937d973e6498ab315e8c3eb1ea670699be3553f15.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": "060818e1bbcfcb1ef93dbdc81ddc1ae9c0371c6dcebc8d9fa0e1c7a99b9008d1", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce9fe0b1adc4cd76e9950b4dbbebed30147013fd44a3902f71573c496de7d01b", "generation_seconds_batch": 22.657984573044814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4690251052379608, "target_z": 0.10595704383481402, "ce": 6.4515180587768555, "genuineness": 4.168440818786621, "identity": 0.36147117614746094, "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_Pleasure_Ecstasy/060818e1bbcfcb1ef93dbdc81ddc1ae9c0371c6dcebc8d9fa0e1c7a99b9008d1.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": "06a8fa8f7ba4f704dcc654af065f85f0dcfd1326fd88f3113533d496c7d5e401", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f36098c3b4cbe7e91ea20f0e5b3f1f8ec23fcc92b195e9533bada660e218117a", "generation_seconds_batch": 20.611456669983454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12053388357162476, "target_z": -0.464843746949136, "ce": 6.213237762451172, "genuineness": 4.469690799713135, "identity": 0.6351406574249268, "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_Pleasure_Ecstasy/06a8fa8f7ba4f704dcc654af065f85f0dcfd1326fd88f3113533d496c7d5e401.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "06bdee05209bd6cf91f2028ff4668a939586a2b6774b27f88543600eef309f20", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c469f8d30489b5586814215a9d18fa56d716d88fa57d61d318f5285c71939dc1", "generation_seconds_batch": 19.547768446966074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1531888246536255, "target_z": 1.2265625793224642, "ce": 6.475345611572266, "genuineness": 3.8797430992126465, "identity": 0.4954982399940491, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/06bdee05209bd6cf91f2028ff4668a939586a2b6774b27f88543600eef309f20.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "06be6c9a20d1e85ed14fbe1b2c830e24fd939c7ecdc4432fc91c062d05b3e5c4", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1660438d77e4249bea827c6db75402b51ea22460f3737f77d6b933ce68936853", "generation_seconds_batch": 20.04060266003944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9862468242645264, "target_z": 0.9531249145758078, "ce": 6.252951145172119, "genuineness": 4.570107460021973, "identity": 0.6973872780799866, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/06be6c9a20d1e85ed14fbe1b2c830e24fd939c7ecdc4432fc91c062d05b3e5c4.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": "07004350fb3c55e5dedff9f324868831c6c713b18a0ef0f4d14d37a64a29d019", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b2a2e9a8e313b60d34e90eb4d679db98a4501f7738e8b384ef833e51e204a92", "generation_seconds_batch": 20.57760534004774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.043484091758728, "target_z": 1.046874987796544, "ce": 6.165581703186035, "genuineness": 4.331617832183838, "identity": 0.625935971736908, "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_Pleasure_Ecstasy/07004350fb3c55e5dedff9f324868831c6c713b18a0ef0f4d14d37a64a29d019.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": "075feae8575b66d7125b252219a32e3ed7c4355b10bb63349658b5b65214a2e1", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5a88b8d02dcb71832a1e3b0d482c59f94ee53c9d1a66817f1d875c7fce8a5575", "generation_seconds_batch": 15.866696872981265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8169201016426086, "target_z": 0.67578126525432, "ce": 6.284721851348877, "genuineness": 4.557555198669434, "identity": 0.7374155521392822, "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_Pleasure_Ecstasy/075feae8575b66d7125b252219a32e3ed7c4355b10bb63349658b5b65214a2e1.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": "079e3fba882ff6a888372b14a4eadf0718d2e79c2674cb6fcbcc3b899c803e71", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7edf4225a24ce22c22fb08b5711261132c3e2c05f926bad0540c595726d7e14d", "generation_seconds_batch": 20.57760534004774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.766837477684021, "target_z": 0.5937499267792639, "ce": 6.284721851348877, "genuineness": 4.381826400756836, "identity": 0.7188968658447266, "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_Pleasure_Ecstasy/079e3fba882ff6a888372b14a4eadf0718d2e79c2674cb6fcbcc3b899c803e71.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": "07db019dcf01e942916215057257db1f00fe52c070a6e32d8af50ff2162e0af6", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "313999ce1acf40d2696c79ad6f60b69c1f1a7ab1b8c6cbcd14f9910b23e6861e", "generation_seconds_batch": 20.68835086992476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8622329235076904, "target_z": 0.7500000488138241, "ce": 6.308549880981445, "genuineness": 4.331617832183838, "identity": 0.7165524363517761, "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_Pleasure_Ecstasy/07db019dcf01e942916215057257db1f00fe52c070a6e32d8af50ff2162e0af6.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": "084d98b259fae71f77d05add17d8de6e3cd7b67387ca245695b504b81dfcc8a0", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1c9e89a6d29ea56bb09516a32842a2bb5a8f4ddabe9431772752c0d673014e5b", "generation_seconds_batch": 15.72289074701257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7000607252120972, "target_z": 0.4843749389827199, "ce": 6.038498878479004, "genuineness": 4.3504462242126465, "identity": 0.6911178231239319, "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_Pleasure_Ecstasy/084d98b259fae71f77d05add17d8de6e3cd7b67387ca245695b504b81dfcc8a0.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "085b6f128338ee9f7dc614fb1510083eef1e750e9032412fcf394d3cfa5fe341", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "727bf3f5bc597b3ac252848ed14b503739ebb311c56d38bc880e6532f82df3fc", "generation_seconds_batch": 17.44420046498999, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.305821418762207, "target_z": 1.4765625793224642, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.8043888807296753, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/085b6f128338ee9f7dc614fb1510083eef1e750e9032412fcf394d3cfa5fe341.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "08793b61cb57e53be750822df4aa4a5c3901b169d2da1590f72fae51600c1db0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "43edac97c2ec835a7604f1c799a83a73941e0987a9492845656dcc9b739e5efa", "generation_seconds_batch": 20.9643388929544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.707215428352356, "target_z": 0.49609377135604804, "ce": 5.816103935241699, "genuineness": 3.8169827461242676, "identity": 0.33888623118400574, "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_Pleasure_Ecstasy/08793b61cb57e53be750822df4aa4a5c3901b169d2da1590f72fae51600c1db0.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "087dc9a553bfd16002744fff8bbd5dedce7cbcb3550ce4cb5b94ae8033da79a3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "16038e2c5d764f2851b539091def5431fdf6d32022cfc7c5513ed299ee698dff", "generation_seconds_batch": 19.219897122005932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7589493989944458, "target_z": 2.218750024406912, "ce": 6.24500846862793, "genuineness": 4.507347106933594, "identity": 0.6484769582748413, "hypothesis": "La porte 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_Pleasure_Ecstasy/087dc9a553bfd16002744fff8bbd5dedce7cbcb3550ce4cb5b94ae8033da79a3.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "095843f2ce9f57279dfc51e83d7c89b8d3a06aa4299248b0385115b44de63845", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "0887fd8d09a59850bfaf8bae8d4003c5b9a34b94b2b03253fff29518470e446a", "generation_seconds_batch": 15.653530015028082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3249003887176514, "target_z": 1.5078124084740798, "ce": 6.197352409362793, "genuineness": 4.582659721374512, "identity": 0.5149661302566528, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/095843f2ce9f57279dfc51e83d7c89b8d3a06aa4299248b0385115b44de63845.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "0971655eaeb2ddcae1107b3b460447d7df0692b5238dceeeb1e1f7b75d9b8ad5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8ff3e15495fe345f1194b7825c2a9f4f9ea9440480129f6ea944161723be2761", "generation_seconds_batch": 15.609294977970421, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4615723490715027, "target_z": 0.09375002440691203, "ce": 6.316492557525635, "genuineness": 4.632867813110352, "identity": 0.36884382367134094, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/0971655eaeb2ddcae1107b3b460447d7df0692b5238dceeeb1e1f7b75d9b8ad5.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "097453ebb6ee7c06d43eded1049fde01b97017a4434daf67510b25236aff766e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "9fe2dd8c079923f4733d9f959a956a5ceda85afa9512b5bcf1a68ff4663fa194", "generation_seconds_batch": 17.70384741795715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5903561115264893, "target_z": 0.3046875427120961, "ce": 6.403861999511719, "genuineness": 4.068024158477783, "identity": 0.5548580884933472, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/097453ebb6ee7c06d43eded1049fde01b97017a4434daf67510b25236aff766e.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "09ff888b806fe5e3ea7975d342c7ac3641809ba4886f533beea3bfe48ccfe72d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8076dbb27d6727aa6619508bbc134a2d6063795283cbd5e05c1720decf976de3", "generation_seconds_batch": 19.519940795958973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0260562896728516, "target_z": 2.6562497803377916, "ce": 5.895530700683594, "genuineness": 4.137060642242432, "identity": 0.4211912155151367, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/09ff888b806fe5e3ea7975d342c7ac3641809ba4886f533beea3bfe48ccfe72d.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "0a1f2a8001de2b0cbb7f25e96d5f4246cef2b1de3b2b95f916f13263fed32fa1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c01fa0c69bcfdad38d1eec25c3f1a656ee31cd2e201932f016082ac521b892dc", "generation_seconds_batch": 19.672999900998548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5586191415786743, "target_z": 1.8906250610172801, "ce": 6.149696350097656, "genuineness": 4.168440818786621, "identity": 0.020667582750320435, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/0a1f2a8001de2b0cbb7f25e96d5f4246cef2b1de3b2b95f916f13263fed32fa1.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": "0b000c883ff53f79098096a6a75c04e43dca4ff424a64a8141dff90c8b321b12", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6d3289d0105913289a4a02e30c400094f92556ed70abd735307510f8c39f8d4d", "generation_seconds_batch": 15.227206059033051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3724372982978821, "target_z": -0.05224607048716196, "ce": 6.197352409362793, "genuineness": 4.331617832183838, "identity": 0.5650087594985962, "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_Pleasure_Ecstasy/0b000c883ff53f79098096a6a75c04e43dca4ff424a64a8141dff90c8b321b12.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "0b23fcec7df454d0be8d67574568f4aeb16f918a376c1e6060b4365d1165aa3f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "72904c40d980e8d1067d9c2a3499c93b06f7fe440655a74f7cb66af9f0f4f234", "generation_seconds_batch": 15.602854548022151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5832014083862305, "target_z": 0.2929687103387679, "ce": 6.515059471130371, "genuineness": 4.20609712600708, "identity": 0.6440979242324829, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/0b23fcec7df454d0be8d67574568f4aeb16f918a376c1e6060b4365d1165aa3f.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "0b8ca37157b883e0b1d0385d3b7ddc045e5242eb0dd3880881a67572a3814ce5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fc8f664d8d0b289a1f95e2aa8052b93915f699d3b003f8362dc5f69ccb8a6db5", "generation_seconds_batch": 23.32123678608332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9814771413803101, "target_z": 0.9453125549155521, "ce": 6.403861999511719, "genuineness": 4.250029563903809, "identity": 0.3196280896663666, "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_Pleasure_Ecstasy/0b8ca37157b883e0b1d0385d3b7ddc045e5242eb0dd3880881a67572a3814ce5.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "0b9d606cf7cd9b58dcac034534c57fd383873062e09582d00c3e60b217cdb591", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "85c54ddeaf844b471cde98ce71f727deb63f6458de8c7a319b63e92cd5efe287", "generation_seconds_batch": 20.468300423002802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7382189035415649, "target_z": 0.546874987796544, "ce": 6.3641486167907715, "genuineness": 4.381826400756836, "identity": 0.6321139335632324, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/0b9d606cf7cd9b58dcac034534c57fd383873062e09582d00c3e60b217cdb591.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "0c0b598ebfbfc1c92283acf22a026db098733f6723743f5f7d93eaa277f8c5b4", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "923a4963258a1ed17e206241560cd1143e27d0757f6963db2809ce8217383f94", "generation_seconds_batch": 14.68925620103255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.043484091758728, "target_z": 1.046874987796544, "ce": 6.149696350097656, "genuineness": 4.331617832183838, "identity": 0.2787575125694275, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/0c0b598ebfbfc1c92283acf22a026db098733f6723743f5f7d93eaa277f8c5b4.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "0c4878a68a8e567f4d041294a94a743667c7c0b30915434114f74ea467fccc74", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "aff63e0cbd9cb72bfc6ab4b15c429deec594bf2c8c6b549f87d5c5b06585dd85", "generation_seconds_batch": 20.376117357984185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4934935569763184, "target_z": 3.4218746949135994, "ce": 5.7247633934021, "genuineness": 3.9048471450805664, "identity": 0.3741461932659149, "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_Pleasure_Ecstasy/0c4878a68a8e567f4d041294a94a743667c7c0b30915434114f74ea467fccc74.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "04da13fccf3f4bef0c53591e1e03c4a487dd0b458ca8beccbc1f92953b9c68a4", "generation_seconds_batch": 15.288596911006607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.003674536943435669, "target_z": -0.656250024406912, "ce": 6.125868320465088, "genuineness": 4.319066047668457, "identity": 0.7046895027160645, "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_Pleasure_Ecstasy/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "0d2e1619a13fb6ddaa1f2e4df5de67b60395c20b776f189cc6357f7df21950ac", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "90f6649b4de944779a135918dd698d410b5b14649bbc354b4f5c10d8f8015d32", "generation_seconds_batch": 15.88257168896962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8121503591537476, "target_z": 0.6679688079664161, "ce": 6.213237762451172, "genuineness": 4.300237655639648, "identity": 0.3397340178489685, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/0d2e1619a13fb6ddaa1f2e4df5de67b60395c20b776f189cc6357f7df21950ac.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "0e303716ced00ad3156fb6d9756df40d8fa1256bc9fcc1391a78f09b046756f1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "97a50afd2c4d6f0505de58dbb4b3f724cab2af3521bd882eb3ad64f5827011d3", "generation_seconds_batch": 22.28444484609645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6063168048858643, "target_z": 1.968750024406912, "ce": 6.268836498260498, "genuineness": 4.6705241203308105, "identity": 0.6761013865470886, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/0e303716ced00ad3156fb6d9756df40d8fa1256bc9fcc1391a78f09b046756f1.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": "0e4ca347895f159ac53d1b2297dcc6a8dcc112e7da7141ddc3df8fc5b722ffd7", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f9211cc23f776bc277b46532336f90fe56f41c52276fbaf9d52a19b264175f51", "generation_seconds_batch": 15.827392244013026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.967167854309082, "target_z": 0.9218750854241922, "ce": 6.109982967376709, "genuineness": 4.582659721374512, "identity": 0.6458078622817993, "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_Pleasure_Ecstasy/0e4ca347895f159ac53d1b2297dcc6a8dcc112e7da7141ddc3df8fc5b722ffd7.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "0e57bb71e02339050dfb08088909c9edfcee48eb455fe09b52b0793381366c5a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7885b24de2c39ac034f7a07ba9a8a56dbc8280953ac90505a3e0e6df3726f010", "generation_seconds_batch": 22.35675036208704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6690572500228882, "target_z": 0.43359372254222395, "ce": 6.2767791748046875, "genuineness": 4.017816066741943, "identity": 0.5019044280052185, "hypothesis": "The 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_Pleasure_Ecstasy/0e57bb71e02339050dfb08088909c9edfcee48eb455fe09b52b0793381366c5a.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "0e8cbf0d76324201c2f44f2504f106c9782a31f64e95d6d7ca2dbeac19559019", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "09e4fcbe46a616ce2f96d3ba3bae564b8edef4123a7b92aa713b268b0de52b84", "generation_seconds_batch": 21.394220271962695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5109214782714844, "target_z": 1.8125000976276482, "ce": 6.316492557525635, "genuineness": 4.432034492492676, "identity": 0.5831374526023865, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/0e8cbf0d76324201c2f44f2504f106c9782a31f64e95d6d7ca2dbeac19559019.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "0ea87345b9f43476d08cdd985c60cd3522aacd6a694944836a1a60c0d420bf66", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c71ab8fdc07b7a5345efc952f5386a8e1975c5a0ed0c72aa8b191ab5769338be", "generation_seconds_batch": 20.859317587921396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.072102665901184, "target_z": 1.0937499267792639, "ce": 5.998785495758057, "genuineness": 4.13078498840332, "identity": 0.2436697781085968, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/0ea87345b9f43476d08cdd985c60cd3522aacd6a694944836a1a60c0d420bf66.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "0eafc86a639b66bf85d8cc2d478d522dabab2810f9ce93c5c917e7605ca9a7dd", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "16b3f17b6d8b2ae6acc2c4f1c5d4e32f5e580c129c82eae0d992114bcfcc1219", "generation_seconds_batch": 21.02013487892691, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5490795373916626, "target_z": 1.874999951186176, "ce": 6.308549880981445, "genuineness": 4.394378662109375, "identity": 0.6352328658103943, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/0eafc86a639b66bf85d8cc2d478d522dabab2810f9ce93c5c917e7605ca9a7dd.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "0ee765612efe3fca3142d2009d90eb83c414cbdba4c8f8d0260e53ca0f8a2617", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4d079cf161fed7fe1ead4bb7750122b858282c1d71dfd0e4c4ba39c69c7cf188", "generation_seconds_batch": 19.975617483025417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9695526361465454, "target_z": 0.9257811676266718, "ce": 6.292664527893066, "genuineness": 3.9927117824554443, "identity": 0.5721319317817688, "hypothesis": "The 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_Pleasure_Ecstasy/0ee765612efe3fca3142d2009d90eb83c414cbdba4c8f8d0260e53ca0f8a2617.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "0efa560f1c030e92cd3cfaff2f0b2856bd886f41e2abd9c88b889a596173c988", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "65baf12a8c75e5ebbd50f45ff80157fe81590fa9aabdbd2f2dbf255b80a828c0", "generation_seconds_batch": 21.342921253992245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3047661781311035, "target_z": -0.16308596114419605, "ce": 6.308549880981445, "genuineness": 4.457139015197754, "identity": 0.5059949159622192, "hypothesis": "De deur 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_Pleasure_Ecstasy/0efa560f1c030e92cd3cfaff2f0b2856bd886f41e2abd9c88b889a596173c988.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "0f2bd0b08a09e957bd9fe1104b859952de9b2661c52e5dbd3ed6cc0d43aaf343", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3904624fcc55b9dd106a4267b3e1f629b92f0ccf00daa4c8f23c6172a8264b46", "generation_seconds_batch": 19.704366652062163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6826331615447998, "target_z": 2.0937501220345602, "ce": 6.070269584655762, "genuineness": 4.20609712600708, "identity": 0.6536025404930115, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/0f2bd0b08a09e957bd9fe1104b859952de9b2661c52e5dbd3ed6cc0d43aaf343.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "0f93da600dcdad728868380ad627fc6c386d31c4c994b2ebb4536329b6f881c3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1f2010087dd20d0ba910041413d4cd7fcbbc77674384a9dae6dd1e1a01b306c2", "generation_seconds_batch": 21.428235108032823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22308391332626343, "target_z": -0.296874987796544, "ce": 6.213237762451172, "genuineness": 4.319066047668457, "identity": 0.6691230535507202, "hypothesis": "De deur 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_Pleasure_Ecstasy/0f93da600dcdad728868380ad627fc6c386d31c4c994b2ebb4536329b6f881c3.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": "0fb05219cd5cfea78edccbb3002b4dda90a66fc5d92049ff19519ff60e81daea", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2716fffdf87497269c079b000b2818a7e0bb92b01f1d30dd5dcd1a139d21318c", "generation_seconds_batch": 16.153870734968223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8479235768318176, "target_z": 0.726562481694816, "ce": 6.427689552307129, "genuineness": 4.143336772918701, "identity": 0.18694767355918884, "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_Pleasure_Ecstasy/0fb05219cd5cfea78edccbb3002b4dda90a66fc5d92049ff19519ff60e81daea.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "103035a8a6ea36b30212538f595ac19e5546a2b7d5bd106ec748d98e4aec3c8d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b71decdea972788adbea52f271c3ae994cf3089c0446e0b5fb0d7e2862bf845d", "generation_seconds_batch": 20.298610443016514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3439794778823853, "target_z": 1.5390624328809919, "ce": 6.213237762451172, "genuineness": 4.168440818786621, "identity": 0.6349986791610718, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/103035a8a6ea36b30212538f595ac19e5546a2b7d5bd106ec748d98e4aec3c8d.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": "108697cb25225b24cccbd7a8ce2f7ba3944e198fc5ed1df161d969904d31a6bd", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "22ab73634d4142ba09a9423bdadcbb9a265e1c0b3cc714b0b9a284eca089d7ca", "generation_seconds_batch": 24.64968965400476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30715107917785645, "target_z": -0.15917968368642, "ce": 6.372091293334961, "genuineness": 4.570107460021973, "identity": 0.6774526238441467, "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_Pleasure_Ecstasy/108697cb25225b24cccbd7a8ce2f7ba3944e198fc5ed1df161d969904d31a6bd.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "10bd04c22a6bceecd68086e8af54e132502eba5f418f4650b3c852cd1c1e04fa", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8943a899dd36ceffe8428769dfdf10664d50a48c4b0ca7caed566116c6b9a705", "generation_seconds_batch": 21.424107028986327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4585912227630615, "target_z": 0.08886717758469198, "ce": 6.252951145172119, "genuineness": 3.7291181087493896, "identity": 0.31769436597824097, "hypothesis": "The 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_Pleasure_Ecstasy/10bd04c22a6bceecd68086e8af54e132502eba5f418f4650b3c852cd1c1e04fa.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": "10c5a21d51ca0663a01abbcaba39032e97e1f27a55438802f464822f7389d0bf", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2989fe5ed44b0d89bcad16dbfe392bea30b1cd33bd85ac0155c5d34d7904a5c5", "generation_seconds_batch": 15.227206059033051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6094351410865784, "target_z": 0.33593746949135994, "ce": 6.348263263702393, "genuineness": 4.394378662109375, "identity": 0.7678563594818115, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/10c5a21d51ca0663a01abbcaba39032e97e1f27a55438802f464822f7389d0bf.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "10cc06458531c41bc92f9a5edbdae6fc8b84bb08e111ad0420b753b556fed240", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "326a89a4666cce12f51970828691380ee7d33e2517a2f673ce53fa07d23f558b", "generation_seconds_batch": 20.7847654230427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.735834002494812, "target_z": 0.5429687103387679, "ce": 6.2767791748046875, "genuineness": 4.287685871124268, "identity": 0.7049791216850281, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/10cc06458531c41bc92f9a5edbdae6fc8b84bb08e111ad0420b753b556fed240.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": "11e0a1a2bd3f5525073ee3dcfc984404eedebb0b58071d8f693265ad5493b4b6", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8e4fae1ebe1e55c963a70699f2f0af219260acba13a41a69636112a3117f5341", "generation_seconds_batch": 16.586311761988327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3105911016464233, "target_z": 1.4843749389827199, "ce": 6.09409761428833, "genuineness": 4.168440818786621, "identity": 0.5415058135986328, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/11e0a1a2bd3f5525073ee3dcfc984404eedebb0b58071d8f693265ad5493b4b6.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "124f39b07556def5cfa0b914a81b857403e11c0205c04f628759809d2472df92", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "93ffa117115fd8d0d3dae38e9b28ee99fabd7c3d99a9e86b257aee93483743d2", "generation_seconds_batch": 20.24148485902697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8829634189605713, "target_z": 2.421875085424192, "ce": 6.0146708488464355, "genuineness": 4.030367851257324, "identity": 0.570772647857666, "hypothesis": "La porte 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_Pleasure_Ecstasy/124f39b07556def5cfa0b914a81b857403e11c0205c04f628759809d2472df92.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "7a790cf65ff2563acc3630eda58da508581325aa7ab6896d59125d15e7db667e", "generation_seconds_batch": 15.261996690067463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46455344557762146, "target_z": 0.09863282241530802, "ce": 6.117925643920898, "genuineness": 4.268857479095459, "identity": 0.5355136394500732, "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_Pleasure_Ecstasy/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "1304c587268170aeb34a39bb7dac72c8ea28b9f2c96613dea2b0230e356f5273", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "49a5a0f967477bc231e87a856aaf6532022d012405b1e03a4886d3f665f66285", "generation_seconds_batch": 15.616663867025636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7334491014480591, "target_z": 0.5390624328809919, "ce": 5.839932441711426, "genuineness": 3.8922953605651855, "identity": 0.07189246267080307, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/1304c587268170aeb34a39bb7dac72c8ea28b9f2c96613dea2b0230e356f5273.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "130bd13477907a02a5bd2b17395d1618010a23187c0fbf22b5b61ce76766686f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b5abcd965a2b62166cac035fd7fc1d96dafd9c0c7ca707cc493086d17cadcbce", "generation_seconds_batch": 15.675224550999701, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8257261514663696, "target_z": 2.328125012203456, "ce": 5.959072113037109, "genuineness": 4.137060642242432, "identity": 0.6227765083312988, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/130bd13477907a02a5bd2b17395d1618010a23187c0fbf22b5b61ce76766686f.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "131e3b788cec98c41869fe829ea6f3c9fd39297edf89cb1e7b761d0b6c1b32fc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1c79e26ad11055185212d22681b744991f085699d158a41299a3e4aea7512da5", "generation_seconds_batch": 21.661287892027758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3916772603988647, "target_z": 1.6171875915259202, "ce": 5.8875885009765625, "genuineness": 3.9801597595214844, "identity": 0.36646971106529236, "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_Pleasure_Ecstasy/131e3b788cec98c41869fe829ea6f3c9fd39297edf89cb1e7b761d0b6c1b32fc.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": "134dfb75ead467d54ae94cae31ea8a4cc06ed84a2df48c20236a5c663ea953d6", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "03aeb7f74f71bd618041211478ab96cf5533a4f6385df8941b4893af1dec2613", "generation_seconds_batch": 16.21223073604051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.105491042137146, "target_z": 1.1484374206775358, "ce": 6.157639026641846, "genuineness": 4.086852550506592, "identity": 0.6238003969192505, "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_Pleasure_Ecstasy/134dfb75ead467d54ae94cae31ea8a4cc06ed84a2df48c20236a5c663ea953d6.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "136c7d921ca9174c951e388f3a907daeaef40260f8998c0a0e15e2a7fdb7ff8c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8186888223fd7b35068a6ab966480835c971dd409f510f6adaec5debdf119618", "generation_seconds_batch": 21.106062615057454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5586191415786743, "target_z": 1.8906250610172801, "ce": 6.157639026641846, "genuineness": 4.124508857727051, "identity": 0.680216372013092, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/136c7d921ca9174c951e388f3a907daeaef40260f8998c0a0e15e2a7fdb7ff8c.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": "14548a1078e786c23fe4a80f035d9cff8dc336f27cd59ef28b16c8f0349ac6d9", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "aa6a47f3f4e34fc6f7623c330a99012a5e64c8c05d86c8cf213cfe26ba7d06bd", "generation_seconds_batch": 22.657984573044814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29820775985717773, "target_z": -0.173828126525432, "ce": 6.53094482421875, "genuineness": 4.13078498840332, "identity": 0.45191189646720886, "hypothesis": "The road turns left behind the bridge. Keep going until you reach the small wooden gate. I will meet you on the other side.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/14548a1078e786c23fe4a80f035d9cff8dc336f27cd59ef28b16c8f0349ac6d9.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "14d23124f370e2f305f7eb1d13d9c23cfaea0ec1dc722ab7b84f44c5b10e1167", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2fcbb05f771035d5115c8a7c9ddd6f8e5efd5b6de3760f72d758e2b5766d7b00", "generation_seconds_batch": 19.776148005970754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.720791220664978, "target_z": 2.156249975593088, "ce": 6.332377910614014, "genuineness": 4.362998008728027, "identity": 0.6344301700592041, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/14d23124f370e2f305f7eb1d13d9c23cfaea0ec1dc722ab7b84f44c5b10e1167.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "1519b9fdd6bb5aad588c25a729ee042f9bded0914631118c356657b765b43582", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8bd46bc51d4d40ff3db7dbe9d9904f86b45c2c392e8f8688a82cfe843a1237eb", "generation_seconds_batch": 21.136422121082433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9051607847213745, "target_z": 0.8203124572879039, "ce": 6.197352409362793, "genuineness": 3.7667744159698486, "identity": 0.45346754789352417, "hypothesis": "The 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_Pleasure_Ecstasy/1519b9fdd6bb5aad588c25a729ee042f9bded0914631118c356657b765b43582.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "154775139f348e80063f39e64a07bac2c0a84e149dd0a9732b8a07871cc896db", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "169101d7964d33938a8c3f8c8763091da1a462ed6a7e710f2db64c67a4750d85", "generation_seconds_batch": 16.465363500989042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8908514976501465, "target_z": 0.796874987796544, "ce": 6.475345611572266, "genuineness": 4.068024158477783, "identity": 0.2662874758243561, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/154775139f348e80063f39e64a07bac2c0a84e149dd0a9732b8a07871cc896db.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "2bb5876bc53c29cd48c86595ddf67bdeccf4ca625fc9d97f285bbf6e63dcd478", "generation_seconds_batch": 16.903221936896443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09430015087127686, "target_z": -0.507812506101728, "ce": 6.23706579208374, "genuineness": 4.432034492492676, "identity": 0.5658696889877319, "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_Pleasure_Ecstasy/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "156848d6dedf083ca8e8dcef726ad6268ada3b214707fd5b57143961776ac2e6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1722b9367bdac4e4d8781988b104a1066b43f21838043c22d0e6908b37396eb5", "generation_seconds_batch": 20.176805865950882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9862468242645264, "target_z": 0.9531249145758078, "ce": 6.435632705688477, "genuineness": 4.394378662109375, "identity": 0.7292695641517639, "hypothesis": "Hum hum hum hum. J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.21052631578947367, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/156848d6dedf083ca8e8dcef726ad6268ada3b214707fd5b57143961776ac2e6.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "15cc187cdf6511b206d54c39dcfc7e516ef35a826ae9e3fe3ca57e30d52ccf9a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "beb1c6e9fc2d3873510ad7ca6ed8febb27ae838e94bd9c7b7005b09119d7257f", "generation_seconds_batch": 16.192729750066064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18492576479911804, "target_z": -0.359374987796544, "ce": 6.292664527893066, "genuineness": 4.149612903594971, "identity": 0.7076944708824158, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/15cc187cdf6511b206d54c39dcfc7e516ef35a826ae9e3fe3ca57e30d52ccf9a.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "16a9cdbecc22bba3e1b8f20625d59c8d8efe6534318c1a64198f51dd3cd42fe3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a5cf57bcd1cc8a6a493b1649e745ae07228c8e0a5e322a1db88ec4dab6b091b2", "generation_seconds_batch": 21.065343674039468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.072102665901184, "target_z": 1.0937499267792639, "ce": 6.078212261199951, "genuineness": 4.362998008728027, "identity": 0.11554384231567383, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/16a9cdbecc22bba3e1b8f20625d59c8d8efe6534318c1a64198f51dd3cd42fe3.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "1716b6b998cc34b51f5d8d36483f8489fd840471a64ec1dc779de952e62a8903", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "48a21e4b6b65782fe442169a42387f6c030a966686eb0d9154b3ec82e3750ea8", "generation_seconds_batch": 14.56677855795715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5109214782714844, "target_z": 1.8125000976276482, "ce": 6.300607204437256, "genuineness": 4.15588903427124, "identity": 0.49974489212036133, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/1716b6b998cc34b51f5d8d36483f8489fd840471a64ec1dc779de952e62a8903.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "176b0495a133a67efbe14e821dda6dbc8dd5e3b2c7817e17cd72e387c5534fcb", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b1b0759ce9bf8b0cbe818b3ab6d4558cd4dcef495f31587fa36586ab4178095a", "generation_seconds_batch": 21.362324477988295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2850908935070038, "target_z": -0.195312506101728, "ce": 6.0305562019348145, "genuineness": 4.21237325668335, "identity": 0.5416778326034546, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/176b0495a133a67efbe14e821dda6dbc8dd5e3b2c7817e17cd72e387c5534fcb.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "18b572537966d00edb7778b49369c28e556ec424013bf97b05bf83caca3efa02", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "382a96a8a6052bfabf508be682eb99915d8f1cead70a62bc39fca23c48ff79cc", "generation_seconds_batch": 20.30358464701567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9147003889083862, "target_z": 0.8359375671190081, "ce": 6.4912309646606445, "genuineness": 3.936227321624756, "identity": 0.3582143187522888, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/18b572537966d00edb7778b49369c28e556ec424013bf97b05bf83caca3efa02.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "18e082a7c7ed20d272df25615aae3d2dcd54c837826ea54e67cca3a03e9542d0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a887251843d326f36a1fc84fb615d2e5a0648f418379500e30cb384917f008d4", "generation_seconds_batch": 20.324040377046913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.968819260597229, "target_z": 2.562500097627648, "ce": 6.09409761428833, "genuineness": 4.111956596374512, "identity": 0.6617432832717896, "hypothesis": "I found the little box! It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/18e082a7c7ed20d272df25615aae3d2dcd54c837826ea54e67cca3a03e9542d0.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "1992dc79950a5493db849e9b840497692f6e2f6df87f8c617b01b40780647135", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c46be7af036950b715fb94381fabcd7c03b5ea11d4ee2aa970d2ab80a5f9f55d", "generation_seconds_batch": 21.397837052936666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8693875074386597, "target_z": 0.7617186859318559, "ce": 6.181467056274414, "genuineness": 4.419482707977295, "identity": 0.15451458096504211, "hypothesis": "Je hebt kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/1992dc79950a5493db849e9b840497692f6e2f6df87f8c617b01b40780647135.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "19b17b3919755393969b3172ae910258599eeae2ecf6224898e6398256639bb3", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3a7ecb1f879ae90ab7ef8f7aeb2fb7176dac8980a678d4a76c84d2fb56855379", "generation_seconds_batch": 17.52212583797518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2433554232120514, "target_z": -0.263671873474568, "ce": 6.197352409362793, "genuineness": 4.381826400756836, "identity": 0.5123032331466675, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/19b17b3919755393969b3172ae910258599eeae2ecf6224898e6398256639bb3.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "1a3e70dceecc6ff8ba8fb9fd7fc29f72efbbe1fbbb4590f4e6ad052d451164a6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ef2d54a4df967f0c4896860c2b0586ff47bdb2a71039bfe19deb201d74f1f74e", "generation_seconds_batch": 20.39621389505919, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1674981117248535, "target_z": 1.250000048813824, "ce": 5.863759994506836, "genuineness": 3.948779582977295, "identity": 0.4130626618862152, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/1a3e70dceecc6ff8ba8fb9fd7fc29f72efbbe1fbbb4590f4e6ad052d451164a6.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": "1a726612d492fe3ab5922d0f6f6e9172181e266d6c69302ff0b71cdf9a5ad8d2", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1ce3c7a38bfe6bab2ebeb9257ce9ab3d0eb20da5cdf77ed72226e831225d4fe1", "generation_seconds_batch": 20.515944015001878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3153609037399292, "target_z": 1.492187493898272, "ce": 6.268836498260498, "genuineness": 4.331617832183838, "identity": 0.4714418649673462, "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_Pleasure_Ecstasy/1a726612d492fe3ab5922d0f6f6e9172181e266d6c69302ff0b71cdf9a5ad8d2.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "1a77560bdf2c582fa5581110d27cc0fcf42cafd4ce10018c19cf212817a2d8c4", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "785b80a637d999b548bc4266003b811e979fb9cd072706f7f80afab6a0e207e0", "generation_seconds_batch": 20.711823081946932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.0034801065921783447, "target_z": -0.667968759152592, "ce": 6.0305562019348145, "genuineness": 4.068024158477783, "identity": 0.6433887481689453, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/1a77560bdf2c582fa5581110d27cc0fcf42cafd4ce10018c19cf212817a2d8c4.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "1aaac6f5fbe48b379e1bd6678978e6a15f63228aae0285e5d99b3ae5a24c96ca", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "59087760a92dc6a6a589665070ce5741c3df7ac6df1ffdce0ea4676dbb4999fc", "generation_seconds_batch": 19.432867628056556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.138879418373108, "target_z": 1.2031249145758078, "ce": 6.141753673553467, "genuineness": 4.168440818786621, "identity": 0.6841692924499512, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/1aaac6f5fbe48b379e1bd6678978e6a15f63228aae0285e5d99b3ae5a24c96ca.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "1b3e984dabc81f14dfd32559276d7b5a94fa623236272010fdc926ec19d8cd32", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d3e817e76bca65547a63c8c3eddc1514b25d608f121a5bf65fc80db866007adc", "generation_seconds_batch": 21.64669295202475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4159614145755768, "target_z": 0.01904295616518598, "ce": 6.165581703186035, "genuineness": 4.720732688903809, "identity": 0.48567599058151245, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/1b3e984dabc81f14dfd32559276d7b5a94fa623236272010fdc926ec19d8cd32.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "1ba6e837f70d5911c553213b475de433c99c86d07730dbfb74703ac600c2f304", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7763eeca8331e321aa72e15bc8316a8a17824e27abfaa79bee6af746563c0777", "generation_seconds_batch": 21.742345917969942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2648193836212158, "target_z": -0.228515620423704, "ce": 6.197352409362793, "genuineness": 4.306513786315918, "identity": 0.615025520324707, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/1ba6e837f70d5911c553213b475de433c99c86d07730dbfb74703ac600c2f304.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "1c08376d53af082f546a438bfe550ed3c1d555ed1f6c0c700a75822f8d8bc644", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "31d75083450c6aae3286bf18ee0216e0993d99ae5975bcbcbc9b2ad1e04d9e57", "generation_seconds_batch": 20.08693754998967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8359991312026978, "target_z": 0.7070311920335839, "ce": 6.133810997009277, "genuineness": 4.375550270080566, "identity": 0.6384143829345703, "hypothesis": "La porte 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_Pleasure_Ecstasy/1c08376d53af082f546a438bfe550ed3c1d555ed1f6c0c700a75822f8d8bc644.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "5da447b07d3c7448349442716278fe3596b6b35e8474d4436565422f773b0835", "generation_seconds_batch": 16.156681386986747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35067522525787354, "target_z": -0.08789060822024797, "ce": 6.268836498260498, "genuineness": 4.432034492492676, "identity": 0.6965509653091431, "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_Pleasure_Ecstasy/1d559e6da25f8bbacc3b53d5880369445633ce7ab0125ca7b07093108b8c8de3.mp3" }, { "id": "heldout-de-1", "language": "de", "sentences": [ "Die Schlüssel liegen auf dem Küchentisch.", "Ich suchte in der Schublade... dann neben dem Fenster.", "Nimm sie mit, wenn du gehst." ], "text": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade... dann neben dem Fenster. Nimm sie mit, wenn du gehst.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-de-1", "key": "1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "a53535bae8185f8d9fe2d9f23ce1d1749aff3dbfc46bc6e62dade27da919358c", "generation_seconds_batch": 16.901978828012943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08237573504447937, "target_z": -0.527343746949136, "ce": 6.395919322967529, "genuineness": 4.419482707977295, "identity": 0.46771901845932007, "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_Pleasure_Ecstasy/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "1dd2a19a54feab76484cd7a8ffdd39de7cb8f3cc86461b17794ab5b6fef43e54", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e7f8473e3b4a9153f7e848704a6683037525adcebd2719de82e49128633e5da6", "generation_seconds_batch": 20.242286566994153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9147003889083862, "target_z": 0.8359375671190081, "ce": 6.284721851348877, "genuineness": 4.105680465698242, "identity": 0.24492564797401428, "hypothesis": "The 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_Pleasure_Ecstasy/1dd2a19a54feab76484cd7a8ffdd39de7cb8f3cc86461b17794ab5b6fef43e54.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": "1dda87dbf9a78b57f6053a9d77499b51661f6e5b971a7ecc3e40c0fe677bf90e", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "944163f5d1a32a37222f89390e64c2fcc3da4d6d13570d7df34a97a968f76cd2", "generation_seconds_batch": 15.8486776399659, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07045131921768188, "target_z": -0.546874987796544, "ce": 6.268836498260498, "genuineness": 4.419482707977295, "identity": 0.41796553134918213, "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_Pleasure_Ecstasy/1dda87dbf9a78b57f6053a9d77499b51661f6e5b971a7ecc3e40c0fe677bf90e.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "1e5211b6d024978687f62161a0e5927af70b047a1e0bc62648d8539247384d50", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fcfa8292ce554cce23ee784ec87e4746524231d04f377baf378fe3d6bc5ef240", "generation_seconds_batch": 17.70384741795715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6654798984527588, "target_z": 0.42773430635555987, "ce": 6.4515180587768555, "genuineness": 4.143336772918701, "identity": 0.5676374435424805, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/1e5211b6d024978687f62161a0e5927af70b047a1e0bc62648d8539247384d50.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "a923772183f5333d40c5a2729ea440d101ea7ec25d8ec320f1f39dc82a5436c1", "generation_seconds_batch": 16.156681386986747, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.567699670791626, "target_z": 0.26757810211851996, "ce": 6.332377910614014, "genuineness": 4.406930446624756, "identity": 0.6919262409210205, "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_Pleasure_Ecstasy/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "1f869ce1ad050a25ac89a3bf2184b5cdbf0c7cb9eb30ba7cbc91b8a514a648ac", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "85ac3652dffd2f9016a53051978750ed38fb2105bd066e415b1297f89b37d472", "generation_seconds_batch": 20.39621389505919, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8288445472717285, "target_z": 0.6953125549155521, "ce": 5.879645347595215, "genuineness": 3.923675537109375, "identity": 0.4676327407360077, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/1f869ce1ad050a25ac89a3bf2184b5cdbf0c7cb9eb30ba7cbc91b8a514a648ac.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "1fc67094302554d67ae5cd0bce9d290df0c03b4f8e34933f117a99d2bd577c62", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0332c4e19d89269c06e11a59d28ab6fb7e889ecd541955b95e1cbc0c4c77d2bd", "generation_seconds_batch": 22.538327678921632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11337924003601074, "target_z": -0.47656248169481596, "ce": 6.2767791748046875, "genuineness": 4.570107460021973, "identity": 0.6481747031211853, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/1fc67094302554d67ae5cd0bce9d290df0c03b4f8e34933f117a99d2bd577c62.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": "1fddc167da9dd7387c1f419e9096e881d580fbbf4f3c4b044a3b8b779b68ef71", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f08cfec1e8d2d48e99ba4553dc322c25cd3bc9d6f4342765295358848d6bf77a", "generation_seconds_batch": 15.41321358201094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12411120533943176, "target_z": -0.458984379576296, "ce": 6.403861999511719, "genuineness": 4.381826400756836, "identity": 0.3493671417236328, "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_Pleasure_Ecstasy/1fddc167da9dd7387c1f419e9096e881d580fbbf4f3c4b044a3b8b779b68ef71.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "20275eb278e350eefa7411e4cbe108a21d3cbe505abefecfaeb81405bea61f78", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ebf68c33ed9436f1046f489121d7ab57266b3cd5336d32afb04e156f334895be", "generation_seconds_batch": 20.667333946097642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3296701908111572, "target_z": 1.515624963389632, "ce": 6.022613525390625, "genuineness": 3.9425034523010254, "identity": 0.22750282287597656, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/20275eb278e350eefa7411e4cbe108a21d3cbe505abefecfaeb81405bea61f78.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "2042aef65f148bb21f99b915816073e319219197479c923039552eb7a7f53aa6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6f8b95df37c7fc977059dae4c007932047d672a23237ef857b8db9959df1efe0", "generation_seconds_batch": 22.56392724404577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3926342725753784, "target_z": -0.0191650395391975, "ce": 6.332377910614014, "genuineness": 4.432034492492676, "identity": 0.6708201169967651, "hypothesis": "De deur 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_Pleasure_Ecstasy/2042aef65f148bb21f99b915816073e319219197479c923039552eb7a7f53aa6.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "2135f2d1d9dfe2f119d076f8bcdb448920da97e23465874c1bd43cec1eeb47e1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "afd71111ff1ef42b484eb1b8ae79859a94bf3be6fb8e4739204c93671ef87542", "generation_seconds_batch": 20.01310966699384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3572336435317993, "target_z": -0.07714844283901201, "ce": 6.133810997009277, "genuineness": 4.21237325668335, "identity": 0.43471577763557434, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2135f2d1d9dfe2f119d076f8bcdb448920da97e23465874c1bd43cec1eeb47e1.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "21365f49973b2f9c24e19e48128cbbce013b36503106f788ef56e8f5bd5d91a4", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cf1bc507f64f3348212ec2e3338754e6c4645a17fd26b26c3abe5c2d84e5c362", "generation_seconds_batch": 20.270661474089138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.091181755065918, "target_z": 1.124999951186176, "ce": 6.356205940246582, "genuineness": 4.419482707977295, "identity": 0.5803917050361633, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/21365f49973b2f9c24e19e48128cbbce013b36503106f788ef56e8f5bd5d91a4.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "213be828af3d93f6b30c1f1c8a7c3e7048c6e36a77d1f737ebe753ef28477bde", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "73f5922138e91ce5ee10fd089764cc221ef86120a33db853569b502bc4e82167", "generation_seconds_batch": 20.584658568026498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.320130705833435, "target_z": 1.500000048813824, "ce": 6.046441555023193, "genuineness": 3.7416701316833496, "identity": 0.5918299555778503, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/213be828af3d93f6b30c1f1c8a7c3e7048c6e36a77d1f737ebe753ef28477bde.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "227a546ded90c20298d6ef161f8ab3546831ca64df52f266bf86c114000b34d9", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2fd30f608b1b5e2d04842a84ead334f27cfd1681665696226573f2ba2887b566", "generation_seconds_batch": 14.645402089925483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5633889436721802, "target_z": 1.8984376159328322, "ce": 6.252951145172119, "genuineness": 4.2374773025512695, "identity": 0.6680452227592468, "hypothesis": "La porte 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_Pleasure_Ecstasy/227a546ded90c20298d6ef161f8ab3546831ca64df52f266bf86c114000b34d9.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "229b0ee06951f5e560dbfc78a56b4b71732962185a80bf8683373556804f3991", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "391c3f629bb92358eb61b671279e83e7ec4f33d23e7d58f69067773645cbd35a", "generation_seconds_batch": 17.01019164500758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7692223787307739, "target_z": 0.5976562042370399, "ce": 6.181467056274414, "genuineness": 4.469690799713135, "identity": 0.19354848563671112, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/229b0ee06951f5e560dbfc78a56b4b71732962185a80bf8683373556804f3991.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "229cbd468476b8113624945ba12f28abf5b173175f8c56341490534d3614399b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e6097dc5f29f9f3809e0feb431f9544e12347f937e86e37169160cde1ce7ec77", "generation_seconds_batch": 14.731536427047104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8717724084854126, "target_z": 0.7656249633896319, "ce": 6.24500846862793, "genuineness": 4.406930446624756, "identity": 0.11297578364610672, "hypothesis": "De deur 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_Pleasure_Ecstasy/229cbd468476b8113624945ba12f28abf5b173175f8c56341490534d3614399b.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "22b4e58bface8182e04622ba726cf3c9b7b19865a2e80bb4dc2d848f5506ff72", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e6764b7a3b8758621e6c5a2a1ab297d137f5005d23105bf31873e49c2470360e", "generation_seconds_batch": 19.667258245055564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.720791220664978, "target_z": 2.156249975593088, "ce": 6.308549880981445, "genuineness": 4.413206577301025, "identity": 0.5500901937484741, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/22b4e58bface8182e04622ba726cf3c9b7b19865a2e80bb4dc2d848f5506ff72.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "22c7ef619ad01c87525531955f46b995dfc26aba986ef5a9523a20509c86afdb", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "db319dd84aa2611816af00599fc7a73f7b87d5ef4c7d29f9ef76a3c0f6b6d3f7", "generation_seconds_batch": 17.993122885003686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.676211953163147, "target_z": 0.4453125549155521, "ce": 6.332377910614014, "genuineness": 4.13078498840332, "identity": 0.40853309631347656, "hypothesis": "The 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_Pleasure_Ecstasy/22c7ef619ad01c87525531955f46b995dfc26aba986ef5a9523a20509c86afdb.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "22d1d79c62aa542ecfe91baa40496b9861410663448a3a581dda6eaf39a01a84", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "15ed099a0199ecd85cc0b44dee0e319129a941db274c173672350abcc32817a8", "generation_seconds_batch": 20.50080117501784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.057793378829956, "target_z": 1.070312457287904, "ce": 6.260893821716309, "genuineness": 4.306513786315918, "identity": 0.3455312252044678, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/22d1d79c62aa542ecfe91baa40496b9861410663448a3a581dda6eaf39a01a84.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "2369fe3260bffe4f73eb15930cf909e99bcb148cba3337e66c5f71d589b383fc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5fa31648399b0993b5c30563c490f998b7a15e4f327ecc0b156f55a669d76d48", "generation_seconds_batch": 20.219810937996954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2724330425262451, "target_z": 1.4218750854241922, "ce": 6.300607204437256, "genuineness": 4.444586753845215, "identity": 0.6919762492179871, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2369fe3260bffe4f73eb15930cf909e99bcb148cba3337e66c5f71d589b383fc.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": "239cafdb65d8ecbef6992516b6d1f022d554350606e4b7e0e1e5b43797c00bbc", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "abb38ec969a0144e59d712ef41e1f33866ffe210ee11754d9d78b5dde10d6397", "generation_seconds_batch": 23.549209037912078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5110586881637573, "target_z": 0.17480469588987602, "ce": 6.3641486167907715, "genuineness": 4.570107460021973, "identity": 0.5633004903793335, "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_Pleasure_Ecstasy/239cafdb65d8ecbef6992516b6d1f022d554350606e4b7e0e1e5b43797c00bbc.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "24866fa564fa97bdcafacbc7d5d59fe051351a8b245c74519ba95e2fb08c18d1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "247690cd4cf574532c4ecc1248cfe5056535797f8b4f6c415441137c232824a7", "generation_seconds_batch": 19.551575660938397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8145352005958557, "target_z": 0.671874987796544, "ce": 6.173524379730225, "genuineness": 4.413206577301025, "identity": 0.3440520465373993, "hypothesis": "Die Tür ist noch offen. Ich habe dein Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/24866fa564fa97bdcafacbc7d5d59fe051351a8b245c74519ba95e2fb08c18d1.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "258f059fd0531d1b15fe5eec288d30f5e59206a6f32d4f5589a1c39c063d455d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "df09cfb92682e2526059bd2c52924b68c52db3641c5f64e22d1aab25077abce1", "generation_seconds_batch": 23.18087616597768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.692172646522522, "target_z": 2.109375036610368, "ce": 6.109982967376709, "genuineness": 4.231201171875, "identity": 0.08580616116523743, "hypothesis": "Dit staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.10526315789473684, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/258f059fd0531d1b15fe5eec288d30f5e59206a6f32d4f5589a1c39c063d455d.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "2599f6aec776db6d49d628cbcad382afbfc1652fb26fd5639b6826578c5ef371", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "dc3185d514a6754067de5bbfee39d5e4fef436f3946de8f18cafb49c680767b4", "generation_seconds_batch": 15.614952877047472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3637920618057251, "target_z": -0.06640627745777604, "ce": 6.229123115539551, "genuineness": 4.375550270080566, "identity": 0.4086502194404602, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2599f6aec776db6d49d628cbcad382afbfc1652fb26fd5639b6826578c5ef371.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "25ca64df16c8759a0ac9ea9d69ccccaaeecfc9da8d89f43643f0d53439f25028", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "94cd7c98104bd17cb2e93a48b0860662afd563e050e5319f4da99b8758097757", "generation_seconds_batch": 14.796340096043423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6826331615447998, "target_z": 2.0937501220345602, "ce": 6.2767791748046875, "genuineness": 4.607763767242432, "identity": 0.6162935495376587, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/25ca64df16c8759a0ac9ea9d69ccccaaeecfc9da8d89f43643f0d53439f25028.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "264fca04bbadaabb88f61f95c5aa00b7f406a50052ba8a41a2ca2ace271b7550", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "98db9bc974bf019d6f0443df80706ac03556d8cf0d141e1dfa09fd3a8396ce31", "generation_seconds_batch": 20.357400125009008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9361642599105835, "target_z": 0.8710936737283999, "ce": 6.3641486167907715, "genuineness": 4.193545341491699, "identity": 0.5315908193588257, "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_Pleasure_Ecstasy/264fca04bbadaabb88f61f95c5aa00b7f406a50052ba8a41a2ca2ace271b7550.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": "2669e44a81bd709a3b940b54d731b0d9d5c787d826b3b269d8c822c6cbc8ac07", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b754cc7979056a8ee7b25c7632c0ccfd8025bf51f210f5d1cadfcba1607fa53", "generation_seconds_batch": 22.716148340026848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3304036855697632, "target_z": -0.12109377135604803, "ce": 6.348263263702393, "genuineness": 4.369274139404297, "identity": 0.35794544219970703, "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_Pleasure_Ecstasy/2669e44a81bd709a3b940b54d731b0d9d5c787d826b3b269d8c822c6cbc8ac07.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "c7815f0170743785cdde6a3473d06673aa1d62e572f241f89d733ba5de28d904", "generation_seconds_batch": 17.065223688958213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1753862202167511, "target_z": -0.375, "ce": 6.340320587158203, "genuineness": 4.243753433227539, "identity": 0.3005748987197876, "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_Pleasure_Ecstasy/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.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": "26d76138fc560360468e1a12c4d846e09fca5516eb3fe3089b695e2f4c6f552d", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d67e9f2e9eb18d41ba6a54a536b368b6c69f39edda7dc188e698b927ed838422", "generation_seconds_batch": 17.144625050015748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7954561710357666, "target_z": 0.6406250610172801, "ce": 6.173524379730225, "genuineness": 4.507347106933594, "identity": 0.5794332027435303, "hypothesis": "Bis écris le numéro sur l'enveloppe. Lis-le bien et vérifie les deux derniers chiffres. Appelle-moi quand il aura un moment.", "wer": 0.18181818181818182, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/26d76138fc560360468e1a12c4d846e09fca5516eb3fe3089b695e2f4c6f552d.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "288069973d2f8cac565e62df08e8d20ca3ac35688345152d2edec857e58b3ed4", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9f2d19c605ce12aeef7c2966cf0a28858455ba8144fca29119b34ee1cc791a66", "generation_seconds_batch": 15.172261693980545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1818073987960815, "target_z": 1.273437518305184, "ce": 6.443574905395508, "genuineness": 4.306513786315918, "identity": 0.38045257329940796, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/288069973d2f8cac565e62df08e8d20ca3ac35688345152d2edec857e58b3ed4.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "289c8e32b93bd3933b81608264fbf549d694041db24918ac545c876dcbb2b0c8", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e3b698122ca2412d2ea975d6dbe28863130f828ba7e6b6e5a76af2f5a5e775ba", "generation_seconds_batch": 23.32123678608332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.062563180923462, "target_z": 1.078125012203456, "ce": 6.427689552307129, "genuineness": 4.344170093536377, "identity": 0.2810916006565094, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/289c8e32b93bd3933b81608264fbf549d694041db24918ac545c876dcbb2b0c8.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "28bbb2765039d61155ce138e84a427b842161efdfe456eb1a7c28f1fb55ea95c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "550ea8c4c286cfb1ebd1ed01ee3a4e71b376a613942e95366dc9f614fed13ce0", "generation_seconds_batch": 19.918491133954376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1674981117248535, "target_z": 1.250000048813824, "ce": 6.324435234069824, "genuineness": 4.174716949462891, "identity": 0.3438063859939575, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/28bbb2765039d61155ce138e84a427b842161efdfe456eb1a7c28f1fb55ea95c.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "28dc9a6949e7376f02dd491184484dc4fb2040e4b7e78f71132971aa3c341de8", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "20448f7b6c703070b817743b81643ade0172b55bff7cd0b759847fdfcb21a434", "generation_seconds_batch": 21.60502986307256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7971075773239136, "target_z": 2.281250073220736, "ce": 6.23706579208374, "genuineness": 4.356721878051758, "identity": 0.6048284769058228, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/28dc9a6949e7376f02dd491184484dc4fb2040e4b7e78f71132971aa3c341de8.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "293640087598d0c4701479bb40ecf438d041f86675824389f18c91b17dedc509", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "515eb35ebc3062c65a8fab8197551087a235f2b20ca0c41de278847d421feef4", "generation_seconds_batch": 20.41927737905644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0029410123825073, "target_z": 0.9804686615249438, "ce": 6.062326908111572, "genuineness": 4.149612903594971, "identity": 0.23738646507263184, "hypothesis": "The door is still open. I put your code on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/293640087598d0c4701479bb40ecf438d041f86675824389f18c91b17dedc509.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "295103752212182bcbf6a5b79d98b6bdb4edccddb07d85197e248c8aa53a771f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "bbb5003b2c66c9a8b852eb589188d7980fc733c7fabe353299493007a437c873", "generation_seconds_batch": 20.739772993023507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8734238147735596, "target_z": 2.406249975593088, "ce": 6.1020402908325195, "genuineness": 4.356721878051758, "identity": 0.5774035453796387, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/295103752212182bcbf6a5b79d98b6bdb4edccddb07d85197e248c8aa53a771f.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "2a22d4d512cfa2da007a001d68507cbb84a54e18e45e9ac092b9651524c5c53c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0e9187f1645ac505f110982dd89b4dabf2e2e7e6757174ca8f356dc7699ce7fa", "generation_seconds_batch": 21.322301398962736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6010880470275879, "target_z": 0.32226559601679194, "ce": 6.268836498260498, "genuineness": 4.582659721374512, "identity": 0.4246249794960022, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2a22d4d512cfa2da007a001d68507cbb84a54e18e45e9ac092b9651524c5c53c.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": "2a8b9d953389a3a67b7a70ea18bbed0cbb405de804a5158b0b9d38cd232b35f9", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e3e5e108d2ed38103d57912697fec6b370970b3e2a1a087f7d97032654262a1", "generation_seconds_batch": 16.09404853801243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4997304677963257, "target_z": 0.15624997559308795, "ce": 6.324435234069824, "genuineness": 3.9425034523010254, "identity": 0.3627813458442688, "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_Pleasure_Ecstasy/2a8b9d953389a3a67b7a70ea18bbed0cbb405de804a5158b0b9d38cd232b35f9.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "2a963de03b09b44ea258ac5f762a9bdcf0cb48f9f5fc40285dae9ac8e0fbe970", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d63cc0222c49a8b53f4ccc0297a19b2d53541f621f3f59f385ce7c0bd42fd01b", "generation_seconds_batch": 20.293403872055933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1150306463241577, "target_z": 1.16406253050864, "ce": 6.427689552307129, "genuineness": 4.218649387359619, "identity": 0.31243637204170227, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2a963de03b09b44ea258ac5f762a9bdcf0cb48f9f5fc40285dae9ac8e0fbe970.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": "2a9f87047173a194f4ab91bbd66feee48e0e434b16b111e04a4a7f14ca3f1900", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "04fc0571f4fb1966fb31aa2cba46a0f0e027d78d95678de4ca07586dedc1ce27", "generation_seconds_batch": 24.877125832950696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4726024270057678, "target_z": 0.11181641120765401, "ce": 6.427689552307129, "genuineness": 4.482243061065674, "identity": 0.6306753158569336, "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_Pleasure_Ecstasy/2a9f87047173a194f4ab91bbd66feee48e0e434b16b111e04a4a7f14ca3f1900.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "2adcb785edb6ac05cf58cded00149c2554bc59499793c6b86d473b78b637b08a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6c4c94b5a70175d3a35f06a911afcedb29dc5dc4f742a5b71efffe9127877e59", "generation_seconds_batch": 20.53139939403627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2056562900543213, "target_z": 1.3125000976276482, "ce": 6.340320587158203, "genuineness": 4.231201171875, "identity": 0.40142160654067993, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2adcb785edb6ac05cf58cded00149c2554bc59499793c6b86d473b78b637b08a.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "2aedc10571592d59dc45bf7368351bc217a2c3a204895980609513217f93a77f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ddcf47e9e7dff857e9bb59bf561f129c3596d87cb296233d1f93c47fb70ac6ab", "generation_seconds_batch": 18.007951783947647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.305821418762207, "target_z": 1.4765625793224642, "ce": 6.24500846862793, "genuineness": 4.482243061065674, "identity": 0.45123958587646484, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2aedc10571592d59dc45bf7368351bc217a2c3a204895980609513217f93a77f.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "2b16fb7e885c832024317dfeea9ca2d4ea33617d9af1442c9df30877417d1211", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1f2d526b7c8129f072b4801911089f68cb0a22e812d2010486b9b2e6bd1deb7f", "generation_seconds_batch": 21.342921253992245, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8813120126724243, "target_z": 0.7812500732207361, "ce": 6.086154937744141, "genuineness": 4.331617832183838, "identity": 0.1928299367427826, "hypothesis": "De deur 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_Pleasure_Ecstasy/2b16fb7e885c832024317dfeea9ca2d4ea33617d9af1442c9df30877417d1211.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "2be756dba319d6316f5c73a5bb16b3b0df70c1d6fe14edc479ab589c5a7e7d48", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2b01a0deb0c05ed18382201a07156f03f4baa66b15b732c5410624323296b566", "generation_seconds_batch": 17.71004897810053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8956212997436523, "target_z": 0.8046875427120961, "ce": 5.903473377227783, "genuineness": 4.074300289154053, "identity": 0.48391470313072205, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2be756dba319d6316f5c73a5bb16b3b0df70c1d6fe14edc479ab589c5a7e7d48.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "2be8147030ea860066f24442f1307c755a1b84df04cca282e0a118dc994ee2ed", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a4e3c574e29ea4917567445c79b0ccb078a54c70d4b8878ebffaa8dae65d4f70", "generation_seconds_batch": 19.331196562969126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4015030562877655, "target_z": -0.004638680074197012, "ce": 6.141753673553467, "genuineness": 4.21237325668335, "identity": 0.41546982526779175, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2be8147030ea860066f24442f1307c755a1b84df04cca282e0a118dc994ee2ed.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "2cdf5067a960c686d23649686b10ad614d761a4ca9745468f7afd76541d366f6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3a2817aa520d9c36c1b0111adfac04ab9ce349cf973ca1a440a5bbab4f40b71b", "generation_seconds_batch": 22.67602136696223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3166906237602234, "target_z": -0.14355467148296397, "ce": 6.356205940246582, "genuineness": 4.344170093536377, "identity": 0.6201525330543518, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2cdf5067a960c686d23649686b10ad614d761a4ca9745468f7afd76541d366f6.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "2d72895e72e0d45c741f3842c5c5d7983ed117c122f688483fcf65e31f8a8d91", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "efd9bf90b5247190228541d9676b341a6523917e4b525b1e423db334d8dc92bc", "generation_seconds_batch": 16.192729750066064, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29701530933380127, "target_z": -0.17578126525432003, "ce": 6.109982967376709, "genuineness": 4.3881025314331055, "identity": 0.5728811621665955, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2d72895e72e0d45c741f3842c5c5d7983ed117c122f688483fcf65e31f8a8d91.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "2dbb694b7f05c0bb01af8a3c4fad5e1947db9d907aa771b8a36b8f04fee20598", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3e2602ac9a936cd8d4132a2b85c8fb2959baa442cfb176f8b69703c5d34d9b95", "generation_seconds_batch": 21.086857776041143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2628934383392334, "target_z": 1.406249975593088, "ce": 6.141753673553467, "genuineness": 4.231201171875, "identity": 0.19648247957229614, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2dbb694b7f05c0bb01af8a3c4fad5e1947db9d907aa771b8a36b8f04fee20598.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "2e1a8393d6cec3dc4e1e799ccdd716c31f88e4a9437ee0c306a91e18dcd4c6c9", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "79e83a5a0935517cd8c61ecc6eaafe47f181c8fc7f851d51c1d886067393db3b", "generation_seconds_batch": 22.85376572003588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9020425081253052, "target_z": 2.453125109831104, "ce": 6.109982967376709, "genuineness": 4.356721878051758, "identity": 0.49532097578048706, "hypothesis": "J'ai trouvé la petite boîte! Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2e1a8393d6cec3dc4e1e799ccdd716c31f88e4a9437ee0c306a91e18dcd4c6c9.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "2e65a64189fe7f7e7cf48681341050c64cf7e65733c69bc0d3c8b376bd57ffe7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "131c1cd219d0502db07de6e7b456d0ad5c4a412bd94cbeb685823c70295424d2", "generation_seconds_batch": 19.614285938907415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.339209794998169, "target_z": 1.5312500732207361, "ce": 5.879645347595215, "genuineness": 4.030367851257324, "identity": 0.5211538076400757, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2e65a64189fe7f7e7cf48681341050c64cf7e65733c69bc0d3c8b376bd57ffe7.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "2f3bb8ce484394081127f2b99a9abc8372b2665f98761b6612f392838decb745", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f965342687e6fd947c00b9835931b2d0dfa973aa303022da8b455e6bedbaadd1", "generation_seconds_batch": 19.702283473103307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2867423295974731, "target_z": 1.445312554915552, "ce": 6.054384231567383, "genuineness": 3.9048471450805664, "identity": 0.5064839124679565, "hypothesis": "The 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_Pleasure_Ecstasy/2f3bb8ce484394081127f2b99a9abc8372b2665f98761b6612f392838decb745.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "2f9515fce70dd7f53a33fca51f5da4b110525e02c36436e30ba20b94670eb209", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "552254f4e3dfce487fc9f82286b9528b2fec794c9877441d306a370f1a27cdb2", "generation_seconds_batch": 20.68054711201694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.722442626953125, "target_z": 3.796874987796544, "ce": 5.792276382446289, "genuineness": 4.042920112609863, "identity": 0.48400646448135376, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2f9515fce70dd7f53a33fca51f5da4b110525e02c36436e30ba20b94670eb209.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "2fbfcf34c6b8735d8ad263a4decdc1ef92af839edec39eb937b5abbf8c32a713", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e9df2845cbd81d3ccf7c9f8adc5963bdd6df5c64ca64040df8eca9fa5a5ee7e9", "generation_seconds_batch": 15.653530015028082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.305821418762207, "target_z": 1.4765625793224642, "ce": 6.268836498260498, "genuineness": 4.293961524963379, "identity": 0.5115557312965393, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/2fbfcf34c6b8735d8ad263a4decdc1ef92af839edec39eb937b5abbf8c32a713.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "2ff568a28128e47c6b377b7744376909aa280e1bc8dd48e9c057f29e253bf3f4", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "35a6895b99cca64249f28519e906c18f19d4f84b9eee4d61e776322a57f79fad", "generation_seconds_batch": 20.78287438803818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0928330421447754, "target_z": 2.7656247681343356, "ce": 6.1894097328186035, "genuineness": 4.18099308013916, "identity": 0.5362246632575989, "hypothesis": "La porte 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_Pleasure_Ecstasy/2ff568a28128e47c6b377b7744376909aa280e1bc8dd48e9c057f29e253bf3f4.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "30a26dd74d03fc944835b6383b03002f809c7e49f0e895b07b36cccd94abd365", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f03fd53caaa9a960bc599978437edc3bf73329185dd82fdb108fb68d56d507c2", "generation_seconds_batch": 22.579436086001806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8121503591537476, "target_z": 0.6679688079664161, "ce": 6.483288764953613, "genuineness": 4.093128204345703, "identity": 0.42792463302612305, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/30a26dd74d03fc944835b6383b03002f809c7e49f0e895b07b36cccd94abd365.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "30eb58ffcb384d88f6be6ad8db47b2fcffa969778290ef7ad2402adbf39e67e3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "592497945eb1066ca3d32b36e753be97cb6465962cfd8c30c24e5509861e2db6", "generation_seconds_batch": 19.686490372987464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9576282501220703, "target_z": 0.906249975593088, "ce": 6.252951145172119, "genuineness": 3.8044304847717285, "identity": 0.4842824935913086, "hypothesis": "The door is still open. I put your code on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/30eb58ffcb384d88f6be6ad8db47b2fcffa969778290ef7ad2402adbf39e67e3.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "30edc5b148d0a0e2f09050649b8ee7860970f2bbaa3342006b9cc8e8e59b5fd2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0c7e7f2671783a72a3d32534ad97c0ff72effc47c978a17518f8f22fb0273ab1", "generation_seconds_batch": 21.065343674039468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4966121912002563, "target_z": 1.7890626281362882, "ce": 6.125868320465088, "genuineness": 4.469690799713135, "identity": 0.2681750953197479, "hypothesis": "De deur 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_Pleasure_Ecstasy/30edc5b148d0a0e2f09050649b8ee7860970f2bbaa3342006b9cc8e8e59b5fd2.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": "311acbb3e85467b822eed85e459a0c636c74f61b8add3d0b6a59c10847d0bcdf", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0afae4be4455ec226ec7f71f3c0bd97fc9ab92ef97dcd200c7f2217f33473d1a", "generation_seconds_batch": 16.13663615495898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5539866089820862, "target_z": 0.24511720199160403, "ce": 6.348263263702393, "genuineness": 4.406930446624756, "identity": 0.5468956828117371, "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_Pleasure_Ecstasy/311acbb3e85467b822eed85e459a0c636c74f61b8add3d0b6a59c10847d0bcdf.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "31a230b2085b2717e0b4edc1cb71aff25c121ff6b8820746072439dc644b4482", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f45336a49fef553cee8f5205054f91d90c4c0cecef3da4855ad82d69a6404673", "generation_seconds_batch": 23.348525257082656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7787619829177856, "target_z": 0.6132813140681441, "ce": 6.300607204437256, "genuineness": 4.6203155517578125, "identity": 0.7169162034988403, "hypothesis": "La porte 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_Pleasure_Ecstasy/31a230b2085b2717e0b4edc1cb71aff25c121ff6b8820746072439dc644b4482.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": "31e07a51be58deac79940212d8c2ccfe86808c76179bae7da508458a830b3bad", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ffd53bd10287f26f482b00bdb0c36c5f4b0488e919ed82895b4f5625ed536c6d", "generation_seconds_batch": 15.221329036052339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1770375967025757, "target_z": 1.265624963389632, "ce": 6.41180419921875, "genuineness": 4.482243061065674, "identity": 0.4957885146141052, "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_Pleasure_Ecstasy/31e07a51be58deac79940212d8c2ccfe86808c76179bae7da508458a830b3bad.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "321d6014afa964af0363a2f5c63b0b6772b5a3786146cd2ba5abed0ef41fa6df", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a41d3768a388c58a4d939f1884fc775db11d68eb6cd93ec26ed7cba853bba4e2", "generation_seconds_batch": 20.526376878027804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03467804193496704, "target_z": -0.605468759152592, "ce": 6.221180438995361, "genuineness": 4.545003414154053, "identity": 0.6563734412193298, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/321d6014afa964af0363a2f5c63b0b6772b5a3786146cd2ba5abed0ef41fa6df.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "324b958d945c0a4b4240019017b7425916765e87877a2f570a2933b39ca2ca07", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1a203c3029fae5998a6ee8039da6180558817ebd260764a12b385887627906ce", "generation_seconds_batch": 20.111330024898052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7017122507095337, "target_z": 2.1250001464414723, "ce": 6.221180438995361, "genuineness": 4.595211505889893, "identity": 0.5973861217498779, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/324b958d945c0a4b4240019017b7425916765e87877a2f570a2933b39ca2ca07.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "32933c4f1eb126addef66a543fcf763e6b069b7bb4e89af4e8b77da11c529b76", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "161acdd9b28bac36328c2afbe616cd4396c9e6d68f317c18eb7e5ae11ef265d5", "generation_seconds_batch": 22.224279579007998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0053259134292603, "target_z": 0.9843749389827199, "ce": 6.23706579208374, "genuineness": 4.425758361816406, "identity": 0.5120799541473389, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/32933c4f1eb126addef66a543fcf763e6b069b7bb4e89af4e8b77da11c529b76.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "32d3e6e2262a9509d4ed41ceadee71374e3439b175cbee74b371fb963619ec59", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "09aa466aa1c90462afb55fcdf0e421518852a16186e1bee67883d907c2b91854", "generation_seconds_batch": 16.864387554000132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7875679731369019, "target_z": 2.265624963389632, "ce": 6.181467056274414, "genuineness": 3.9299514293670654, "identity": 0.6623449325561523, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/32d3e6e2262a9509d4ed41ceadee71374e3439b175cbee74b371fb963619ec59.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": "337adf1bb47c73c2d223db428b8d7912e8a74ab1d5a33bcf32a4ee4f79982e32", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b124049ffc7965de683a4494b1da9078eb52b6707a247909c56898a24dabd04f", "generation_seconds_batch": 16.153870734968223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1722677946090698, "target_z": 1.2578124084740798, "ce": 6.372091293334961, "genuineness": 4.293961524963379, "identity": 0.37642037868499756, "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_Pleasure_Ecstasy/337adf1bb47c73c2d223db428b8d7912e8a74ab1d5a33bcf32a4ee4f79982e32.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "3388704c063f7f3158091d6d0e8badbc0ca08a4ea68498c4bf7ea69ed36a0512", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "26c8b9b4f4e78da7cb1c119438a3bcad0bf6037e7c636fae4281621920e1b4c5", "generation_seconds_batch": 16.95383519399911, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8622329235076904, "target_z": 0.7500000488138241, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.576448917388916, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/3388704c063f7f3158091d6d0e8badbc0ca08a4ea68498c4bf7ea69ed36a0512.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "3397cd1e2cc05b1ad80d9b4913b82805301de5f64b4d6d3c1a7b6540486f52e7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "bf5b232bc7777dfe809f8e152216813cc02aaa865c7901667ebabe5ce9aa288a", "generation_seconds_batch": 15.382442999980412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9600131511688232, "target_z": 0.910156253050864, "ce": 6.070269584655762, "genuineness": 4.293961524963379, "identity": 0.4440750181674957, "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_Pleasure_Ecstasy/3397cd1e2cc05b1ad80d9b4913b82805301de5f64b4d6d3c1a7b6540486f52e7.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "33b9396bee3fcb7d6a2dec41e310d8ec55366952a581ee5dc3352af87d8d9508", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "be24dd917aeea3e583fe2a22257e0f4c01dbcd6db525c3660baeb0e4d338fa2f", "generation_seconds_batch": 24.80495679494925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6082427501678467, "target_z": 0.3339844283901201, "ce": 6.467403411865234, "genuineness": 4.2249250411987305, "identity": 0.4160185158252716, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/33b9396bee3fcb7d6a2dec41e310d8ec55366952a581ee5dc3352af87d8d9508.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "33d748e5bc7632baa60d5be7149af1aa18c42ca26a19e89fb405e15b2585daa6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c2d21681e09bc84a19db0a76fbff4ee39eacfaa9ba92cebf87d753bb61925b67", "generation_seconds_batch": 20.456796244950965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1341097354888916, "target_z": 1.195312554915552, "ce": 6.229123115539551, "genuineness": 4.570107460021973, "identity": 0.657168984413147, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/33d748e5bc7632baa60d5be7149af1aa18c42ca26a19e89fb405e15b2585daa6.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "33e7bfdc011580881ad43e841fc5edf4bee2b316b68ad093e0b4c2b1d1a5e729", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "cecce6135f98a02a8ee5c6d3cacfae65b3579e50e176ceeba1526eb96b3050cb", "generation_seconds_batch": 20.324040377046913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.226386785507202, "target_z": 2.9843751342380163, "ce": 5.974957466125488, "genuineness": 4.344170093536377, "identity": 0.5570633411407471, "hypothesis": "I found the little box! It was beside the old window! We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/33e7bfdc011580881ad43e841fc5edf4bee2b316b68ad093e0b4c2b1d1a5e729.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "40d582c66719485e1e6621c2621c38bebdfe1b806a6fa79bc2d82711be0bf7cd", "generation_seconds_batch": 17.734599188086577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02990826964378357, "target_z": -0.61328126525432, "ce": 6.260893821716309, "genuineness": 4.369274139404297, "identity": 0.7659324407577515, "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_Pleasure_Ecstasy/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "341b8a906ec7feb4d2d8ded58a6c6b35b0d7c1b3414d71005dbf090f27880564", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c77c72106c9f7dfedd9a6e81476064931e6359e8684e7109f4af0af7790c00ae", "generation_seconds_batch": 21.063327872077934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.663554072380066, "target_z": 2.062500097627648, "ce": 6.157639026641846, "genuineness": 3.936227321624756, "identity": 0.5792878270149231, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/341b8a906ec7feb4d2d8ded58a6c6b35b0d7c1b3414d71005dbf090f27880564.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "eca9a1c0bf5e60310b59d7d2bc817231d1dab2fb932b0513b59dff26e9c2867a", "generation_seconds_batch": 15.45344557100907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07999083399772644, "target_z": -0.531250024406912, "ce": 6.507116317749023, "genuineness": 4.068024158477783, "identity": 0.34761521220207214, "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_Pleasure_Ecstasy/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "34a3038809711c13e172c6fba241d92093da4751d2faa81b6582f7c3412889b0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4371636b42204d50032ea2a352ad797164a3041b2e7103a6d3bdfac0138298e9", "generation_seconds_batch": 15.552451168070547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5283491015434265, "target_z": 0.20312501220345602, "ce": 6.300607204437256, "genuineness": 4.18099308013916, "identity": 0.5537431836128235, "hypothesis": "The 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_Pleasure_Ecstasy/34a3038809711c13e172c6fba241d92093da4751d2faa81b6582f7c3412889b0.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "34cd20ab2c724276d2410438e0581a3650ca33830c8ca2567a1a6128a933a2c7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6a52787dcfcdab2b19fc478a60fb129c224f42bfdddbae1406b0f25182476e67", "generation_seconds_batch": 23.676110872998834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10145479440689087, "target_z": -0.49609377135604804, "ce": 6.268836498260498, "genuineness": 4.419482707977295, "identity": 0.7728329300880432, "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_Pleasure_Ecstasy/34cd20ab2c724276d2410438e0581a3650ca33830c8ca2567a1a6128a933a2c7.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": "354113831b6d8a30c1a4743f05564d2b038fd46c6167d64a98adf9a9bc4afb3a", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "62215d15bedf0f22f5932de7d07912145306d2396f667c9cd7781b5ea955ffc7", "generation_seconds_batch": 17.762282024952583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4111171364784241, "target_z": 0.011108415503270526, "ce": 6.197352409362793, "genuineness": 4.15588903427124, "identity": 0.5142662525177002, "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_Pleasure_Ecstasy/354113831b6d8a30c1a4743f05564d2b038fd46c6167d64a98adf9a9bc4afb3a.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "355109ea915558ab4120773717c1728a2ff844ab886f6ff273ad4773dd1f8f93", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "fc41c376db52d3a1d78b97444907784e45c40f72e7699c9d041a60171c71c975", "generation_seconds_batch": 21.208136413013563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.739870309829712, "target_z": 2.1875, "ce": 6.046441555023193, "genuineness": 4.293961524963379, "identity": 0.6743297576904297, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/355109ea915558ab4120773717c1728a2ff844ab886f6ff273ad4773dd1f8f93.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "3576791b7fadd2c11000982040406a7fc0605fa189495dc599fe708966332e0d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a1474df103e73619113f1b7c0a5c505202af69b167a05e372bef189720638d2a", "generation_seconds_batch": 20.493809023988433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9576282501220703, "target_z": 0.906249975593088, "ce": 6.205295085906982, "genuineness": 4.068024158477783, "identity": 0.5107589960098267, "hypothesis": "The 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_Pleasure_Ecstasy/3576791b7fadd2c11000982040406a7fc0605fa189495dc599fe708966332e0d.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "357a8096bb1e2d14986fc6dacb21f13dda26c5f7ced6baa9d1503545b890d550", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "890ee9c88a02d77770ffba7c68a0055f52174e932c34f9e5b257f43a32999489", "generation_seconds_batch": 19.522450748016126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.692172646522522, "target_z": 2.109375036610368, "ce": 6.372091293334961, "genuineness": 4.494794845581055, "identity": 0.7005787491798401, "hypothesis": "La porte 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_Pleasure_Ecstasy/357a8096bb1e2d14986fc6dacb21f13dda26c5f7ced6baa9d1503545b890d550.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "35906672322b78e9496a30a314f7b52e876b958e8f4c3e2803a89914c91331e3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b9426d68f16fb8f4369ffbc97d85cb7b90db893ccea07a61acf072dfc8e0bda1", "generation_seconds_batch": 21.562419555033557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.4267168045043945, "target_z": 3.3124997071170554, "ce": 5.772419452667236, "genuineness": 4.093128204345703, "identity": 0.4764951765537262, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/35906672322b78e9496a30a314f7b52e876b958e8f4c3e2803a89914c91331e3.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "35be6aefac9b6d9b21eab52b8bdde453717b306a0a45b9cd61b48eb29081ffcc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "34dff5db8640638b42afc8c471a00b263b6eca2a5bd7f9085feb42f9d9ff0d44", "generation_seconds_batch": 19.776148005970754, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7017122507095337, "target_z": 2.1250001464414723, "ce": 6.284721851348877, "genuineness": 4.017816066741943, "identity": 0.41299861669540405, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/35be6aefac9b6d9b21eab52b8bdde453717b306a0a45b9cd61b48eb29081ffcc.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "35d32cd60eb8970986373271d31280f53ec27de484a100d72f0fce4f14eb19cb", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7bf7d3dcc12c4f0d94108030156d2208061dbe00541ecbfa06466b07d46ded7f", "generation_seconds_batch": 24.234475665027276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.07687246799469, "target_z": 1.101562481694816, "ce": 6.046441555023193, "genuineness": 4.143336772918701, "identity": 0.3376225531101227, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/35d32cd60eb8970986373271d31280f53ec27de484a100d72f0fce4f14eb19cb.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "35fa55b484a3f604444668f6385290ee44938c9a71a166fe954c00fa2d2ce585", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e3b1e41dcf3bac9016a6d04ffa3ad4897bc80df5e16b6a3f569161d963f93b8e", "generation_seconds_batch": 21.275077964994125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2104259729385376, "target_z": 1.320312457287904, "ce": 6.324435234069824, "genuineness": 4.068024158477783, "identity": 0.31273746490478516, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/35fa55b484a3f604444668f6385290ee44938c9a71a166fe954c00fa2d2ce585.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "363ed39ca2b96d89e04ca0104626a306ffddf885f5e24c96a382eeb1b34ad192", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3adfc60041644135c098f886f6a0d71bb375f145bb0cad7cca8f3f80c40866ec", "generation_seconds_batch": 15.370196218951605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1007213592529297, "target_z": 1.1406250610172801, "ce": 6.229123115539551, "genuineness": 4.331617832183838, "identity": 0.7752414345741272, "hypothesis": "La porte 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_Pleasure_Ecstasy/363ed39ca2b96d89e04ca0104626a306ffddf885f5e24c96a382eeb1b34ad192.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "3693fa3bb4ece975ca1434e7be8c800d48eac0a568595de0557421a75d2c4ede", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "754e6e0c4f4feb09af21801e54049a11daea296fe7e203139a84b41b32d16161", "generation_seconds_batch": 20.733183413976803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3327885866165161, "target_z": -0.11718749389827199, "ce": 6.221180438995361, "genuineness": 4.13078498840332, "identity": 0.6702595949172974, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/3693fa3bb4ece975ca1434e7be8c800d48eac0a568595de0557421a75d2c4ede.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": "36ac634b5da20179d14b46be3ce6064454e753421872c1a303f1387b4ac1be95", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8cd0139e9969b9c656b86d64d23a5313df32a317fce223ed2a9620bcbc7674b4", "generation_seconds_batch": 15.827392244013026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1102608442306519, "target_z": 1.156249975593088, "ce": 6.284721851348877, "genuineness": 4.218649387359619, "identity": 0.5395472049713135, "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_Pleasure_Ecstasy/36ac634b5da20179d14b46be3ce6064454e753421872c1a303f1387b4ac1be95.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "37672b92f4b6a58bdef71f8144931ba1ba1e228486e0782c470dc801be4eebc5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2890077889d5978443dd0fce427b18c70a16fcec9723990970415fb9f736e135", "generation_seconds_batch": 22.35675036208704, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5331188440322876, "target_z": 0.21093746949135994, "ce": 6.268836498260498, "genuineness": 4.055472373962402, "identity": 0.2462444305419922, "hypothesis": "The 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_Pleasure_Ecstasy/37672b92f4b6a58bdef71f8144931ba1ba1e228486e0782c470dc801be4eebc5.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "37846ceccc439ce333d06b23d9a4cf3f8c3e2ded9a0dcc0236d04e8a984aa8fe", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0b19de06c4301874c17aca86a3fa4f04db1a3637c82fba57769af0563f0520c5", "generation_seconds_batch": 20.022982187918387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027523398399353027, "target_z": -0.617187493898272, "ce": 6.205295085906982, "genuineness": 4.281409740447998, "identity": 0.5759499669075012, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/37846ceccc439ce333d06b23d9a4cf3f8c3e2ded9a0dcc0236d04e8a984aa8fe.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "386f3fed29d5578d3c99721dd1d117a7b5ee1a2c76e6e7cd9db211989bcf4eda", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f79da86f01cd3fea00fb2c21051f6484bdf0ea4f3737c17e5f2184eb2074a53f", "generation_seconds_batch": 19.42391296196729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0530236959457397, "target_z": 1.0625000976276482, "ce": 6.149696350097656, "genuineness": 4.457139015197754, "identity": 0.08096450567245483, "hypothesis": "De deur 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_Pleasure_Ecstasy/386f3fed29d5578d3c99721dd1d117a7b5ee1a2c76e6e7cd9db211989bcf4eda.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "38c856cee7bad68ef64cfee8b327d6524bb2e63ce2becba08623bcda60c559c4", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "570149edf3e4a07a7c32b9f8aa67f3e8cf4e4c2a3abc3a4e1cf04fe091cdf6db", "generation_seconds_batch": 21.210105127072893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6142049431800842, "target_z": 0.34375002440691205, "ce": 6.308549880981445, "genuineness": 4.381826400756836, "identity": 0.5005111694335938, "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_Pleasure_Ecstasy/38c856cee7bad68ef64cfee8b327d6524bb2e63ce2becba08623bcda60c559c4.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "38f9723c3465ba008894a53cf938819e99782008d5ac14a249a8189b0f155916", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a84071beebd4f536f2ff2c91784d3eacce8e71cd6c1d2c6fe439076002b3d4cb", "generation_seconds_batch": 17.32915079407394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30536240339279175, "target_z": -0.16210939177975203, "ce": 6.149696350097656, "genuineness": 4.507347106933594, "identity": 0.5529998540878296, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/38f9723c3465ba008894a53cf938819e99782008d5ac14a249a8189b0f155916.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "3909ca55754983eafd1965fd3f6a249e96073b033e3c8c8f26dcb792fb186bbb", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d58fb38a1beacf029bd674b01ea4f3aa707e7823b9625394d9315af701a6cbeb", "generation_seconds_batch": 18.32615237601567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5832014083862305, "target_z": 0.2929687103387679, "ce": 6.348263263702393, "genuineness": 4.632867813110352, "identity": 0.5666512250900269, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/3909ca55754983eafd1965fd3f6a249e96073b033e3c8c8f26dcb792fb186bbb.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "39e3d20daeda2baf1946d2ba1ec62eb8f9e28f2122bcae0582969835e9ee8853", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b4ff6f3448006fe00e338ed228cc36ce66e0c1527f8388b6237ebbc3c9851893", "generation_seconds_batch": 17.293376330984756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4059865474700928, "target_z": 1.6406250610172801, "ce": 6.23706579208374, "genuineness": 4.570107460021973, "identity": 0.6273521184921265, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/39e3d20daeda2baf1946d2ba1ec62eb8f9e28f2122bcae0582969835e9ee8853.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "3ab454bb91c3804fb22a86969e1bfc5d604a880411885f18763224fb23282bef", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "362652d809fa722e28292603f1c5a531686437d5f92186d8394f2715d888e7ed", "generation_seconds_batch": 21.446293396060355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5443098545074463, "target_z": 1.8671875915259202, "ce": 6.1894097328186035, "genuineness": 4.080576419830322, "identity": 0.28405505418777466, "hypothesis": "De duur staat nog open! Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/3ab454bb91c3804fb22a86969e1bfc5d604a880411885f18763224fb23282bef.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "3b0cae46e3e7953831cdb1c15655605a125e5c489942b49e829e22907ba371f2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c54df271fa17f9e9ca250e1d60d65dc5dc6347ccc083f6f6681dc8d44cb18ae6", "generation_seconds_batch": 14.526004244107753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6642875075340271, "target_z": 0.42578126525432003, "ce": 6.125868320465088, "genuineness": 4.65797233581543, "identity": 0.3746938705444336, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/3b0cae46e3e7953831cdb1c15655605a125e5c489942b49e829e22907ba371f2.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "3b52b2133099f7804c71d0dd3e591c4d94ace3a24e84547b20db50cc9fa2cf4f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "4eac08f55425102c82435f3f36b4eee9950be670b0b83bee32fadcbd9a8d61c9", "generation_seconds_batch": 20.016108470968902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4442819356918335, "target_z": 0.06542970809333203, "ce": 6.260893821716309, "genuineness": 4.7081804275512695, "identity": 0.6018378138542175, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/3b52b2133099f7804c71d0dd3e591c4d94ace3a24e84547b20db50cc9fa2cf4f.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "a60e9622a85c1ef87bb7acf12e2bcdf6531e80e380f0cbf2f7ce7695c85556c7", "generation_seconds_batch": 15.25386576296296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.006059437990188599, "target_z": -0.652343746949136, "ce": 6.046441555023193, "genuineness": 4.093128204345703, "identity": 0.5342638492584229, "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_Pleasure_Ecstasy/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "3d282380d93b63c38f3da2c7b2b6872499ebd20958e2283c3ba9be59b10115dc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "24bf5d0586822f708b20f96233bff36adc4f002c37652476495582c85424b3b3", "generation_seconds_batch": 20.684196892078035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25826096534729004, "target_z": -0.23925778580493995, "ce": 6.197352409362793, "genuineness": 4.419482707977295, "identity": 0.6082104444503784, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/3d282380d93b63c38f3da2c7b2b6872499ebd20958e2283c3ba9be59b10115dc.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "3d7b13b394f62e7eed15a4e812d6f35879fc7672bf3f1b1f8162b7023c1202b6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9d6f5f45726c8cbcf02ae5b8f9916e7969c87d7b5f14c4ca4b5c9c4c8271b5e2", "generation_seconds_batch": 20.54654459701851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1293399333953857, "target_z": 1.1875, "ce": 6.427689552307129, "genuineness": 3.823258876800537, "identity": 0.261648029088974, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/3d7b13b394f62e7eed15a4e812d6f35879fc7672bf3f1b1f8162b7023c1202b6.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": "3d7ca4fce765892894c9934caf70b201a7d0326f7bc9dd5e0c27c1f1ecc7ea11", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "87324ff6f817af9575c252921d4dd25aaf9c52b7c43b666e128fc2404fb2100d", "generation_seconds_batch": 16.005542194936424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5331188440322876, "target_z": 0.21093746949135994, "ce": 6.173524379730225, "genuineness": 4.356721878051758, "identity": 0.6474151611328125, "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_Pleasure_Ecstasy/3d7ca4fce765892894c9934caf70b201a7d0326f7bc9dd5e0c27c1f1ecc7ea11.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "3dd36a752c71a9a1fd00b75269b536a8ac4d99a4ccd546bcbfaecdfcdf2e6b91", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "998824d7e29331053d5f109bb4717f2f6ef2184012497b146db2edcdd5f1941b", "generation_seconds_batch": 20.584658568026498, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3313214778900146, "target_z": 3.1562497803377916, "ce": 5.927301406860352, "genuineness": 4.137060642242432, "identity": 0.47230294346809387, "hypothesis": "La puerta sigue abierta y he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/3dd36a752c71a9a1fd00b75269b536a8ac4d99a4ccd546bcbfaecdfcdf2e6b91.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "3e17f408ec754507f9be5eaed9d04b4467db0b273bb9c73009c5dce0a66ab45a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d2c669e45199f177f9b1c6a1e3de3936db67d1886fa00e47be0f1300b3279375", "generation_seconds_batch": 20.6454172199592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7406038045883179, "target_z": 0.55078126525432, "ce": 6.427689552307129, "genuineness": 4.256305694580078, "identity": 0.5423261523246765, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/3e17f408ec754507f9be5eaed9d04b4467db0b273bb9c73009c5dce0a66ab45a.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "3f9cabd09099da836c6dcc3814cd42fa57afe71130cb60273c473d072307d62a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "b0ceec73ee3442b3a8b3f79254a0126f420a116caa81b8568cf5b044317bfb41", "generation_seconds_batch": 21.1163593189558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.6461262702941895, "target_z": 3.671874890168896, "ce": 5.71682071685791, "genuineness": 3.848362922668457, "identity": 0.3435395061969757, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/3f9cabd09099da836c6dcc3814cd42fa57afe71130cb60273c473d072307d62a.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "3fbf3dd8a17d2843f8cb22ee8c66b121685abe5e08d6df6b6e4fb2b540f0e7ff", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "22cff8e5425eb4d4fd24efde7388c29cf20d0f8130d7f9c9492ec6f71ca3d9a5", "generation_seconds_batch": 20.947192445979454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.072102665901184, "target_z": 1.0937499267792639, "ce": 6.41180419921875, "genuineness": 4.218649387359619, "identity": 0.5452630519866943, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/3fbf3dd8a17d2843f8cb22ee8c66b121685abe5e08d6df6b6e4fb2b540f0e7ff.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "3ffbb51ac9e22db826ffabab5daf67ef3688576ffd2ca7e89d01a9fee1eeff49", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d128bb48b0f09d3b7527ffb4fabda3f97b6635b41661413365f5bf01e7399e2c", "generation_seconds_batch": 16.70598308404442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1102608442306519, "target_z": 1.156249975593088, "ce": 6.109982967376709, "genuineness": 4.093128204345703, "identity": 0.5344650149345398, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/3ffbb51ac9e22db826ffabab5daf67ef3688576ffd2ca7e89d01a9fee1eeff49.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "409c1a632ecd67cfa7a61d10dbbd49d578e27155f8fde58fe56c03a88befb969", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e5b9fda0dbf821925726a281ea861ba09886038e0e3e24e5b9c150f6b7c16e9d", "generation_seconds_batch": 14.878827093052678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1102608442306519, "target_z": 1.156249975593088, "ce": 6.221180438995361, "genuineness": 4.425758361816406, "identity": 0.4489271342754364, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/409c1a632ecd67cfa7a61d10dbbd49d578e27155f8fde58fe56c03a88befb969.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "41428dad62b00828dd8c72fce39794eff8159c1faef65b73ff57781670be3c5d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "08d872d00d617b85898b309373e60fca6a01355bce4ad4f0c62e8a5da2ded5a7", "generation_seconds_batch": 20.263288798974827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3961370587348938, "target_z": -0.013427755540369032, "ce": 6.475345611572266, "genuineness": 4.218649387359619, "identity": 0.46608102321624756, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/41428dad62b00828dd8c72fce39794eff8159c1faef65b73ff57781670be3c5d.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "4164a21b0d2a4a7690ef5dfb83db4eeef256943c35de7291a712edd3ca049451", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f949dad186904f3caf3f9465eb3c4bc66497598e28b8acd5cca3057c953c4aeb", "generation_seconds_batch": 15.808861505007371, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.582468032836914, "target_z": 1.9296876403397443, "ce": 6.348263263702393, "genuineness": 4.362998008728027, "identity": 0.35574808716773987, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4164a21b0d2a4a7690ef5dfb83db4eeef256943c35de7291a712edd3ca049451.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "417163a000764f70ae243aff99da5becf139190d13a8ca078e1a788c6d7b1991", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f2ab7f207070f8a7d3c522286c87d329367eae86752bf8de367ee49eb44b8717", "generation_seconds_batch": 20.456796244950965, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8860816955566406, "target_z": 0.7890624328809919, "ce": 6.213237762451172, "genuineness": 4.444586753845215, "identity": 0.6418707370758057, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/417163a000764f70ae243aff99da5becf139190d13a8ca078e1a788c6d7b1991.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": "419bfe21b9d1f8b37d58f48e9edec92e8e8bfbfdfdf319f93022eac2333f9f26", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9fb9ad8d9439f11a4765270c2c37077ee7b53aa49b2bc2480c448847c3a3f62e", "generation_seconds_batch": 15.973012748057954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6666723489761353, "target_z": 0.4296874450844479, "ce": 6.205295085906982, "genuineness": 4.482243061065674, "identity": 0.4943392276763916, "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_Pleasure_Ecstasy/419bfe21b9d1f8b37d58f48e9edec92e8e8bfbfdfdf319f93022eac2333f9f26.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "41f07eac537c28da22e7ce10c9b79dd48c158c8b749edb252a78f046a9d0240a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d57d4f6a8b72052b4b2c7bf4972a89c46194fea4299345f953c6669bf5247ddf", "generation_seconds_batch": 14.61827883508522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4584540128707886, "target_z": 1.7265625793224642, "ce": 6.197352409362793, "genuineness": 3.948779582977295, "identity": 0.25987109541893005, "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_Pleasure_Ecstasy/41f07eac537c28da22e7ce10c9b79dd48c158c8b749edb252a78f046a9d0240a.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "420a8faa3eec4f36a6fdc0b76307858b69ac88c6c386db6a2b811fc9b9f3f642", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5cfe5ea6905b0bf214e0b7b95d6bce10b356853caf7eb2b4cd3b1df8642f800d", "generation_seconds_batch": 20.015093515976332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39855921268463135, "target_z": -0.009460460802499267, "ce": 6.252951145172119, "genuineness": 4.444586753845215, "identity": 0.5657832622528076, "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_Pleasure_Ecstasy/420a8faa3eec4f36a6fdc0b76307858b69ac88c6c386db6a2b811fc9b9f3f642.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "42106477ad0aa42e5b70485e4f5a0e527b43365ce96fd1d94f77f058f8e96ce1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "308c0fa532678d55e2ccd210096c30bf10206d7fa2a9595e832c9117093b0011", "generation_seconds_batch": 22.15283786796499, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4155887961387634, "target_z": 0.01843263692277653, "ce": 6.221180438995361, "genuineness": 4.344170093536377, "identity": 0.7224517464637756, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/42106477ad0aa42e5b70485e4f5a0e527b43365ce96fd1d94f77f058f8e96ce1.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "427d4fe523182bf2cc66a702f4b7d1a13ee899d4564314bc64a2a2e011ce496e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8742392b8d74771a88789e8b1419f47c2d55e716dc1cac80fd9a6c25bb6ae736", "generation_seconds_batch": 17.69778294104617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9957864284515381, "target_z": 0.968750024406912, "ce": 6.197352409362793, "genuineness": 4.557555198669434, "identity": 0.5220761299133301, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/427d4fe523182bf2cc66a702f4b7d1a13ee899d4564314bc64a2a2e011ce496e.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": "427ec7d15303f5a2c90ff99b077de44345e6b0de59228480de135e760cedd2c4", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4cb53098341f4fadcb0ac6cf873e5d4902a99ac8ce13df318ae28e7db6909a50", "generation_seconds_batch": 16.193890271009877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7286794185638428, "target_z": 0.5312500732207361, "ce": 6.4912309646606445, "genuineness": 4.7458367347717285, "identity": 0.5062092542648315, "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_Pleasure_Ecstasy/427ec7d15303f5a2c90ff99b077de44345e6b0de59228480de135e760cedd2c4.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "43212aff020a14d7d8adf5a55a649bec6d93e88b6fc933409267b11b4e125e39", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e2a5dcf671098e3f1381a855df9da8868526c64975d1e10a9458288e3f7f9d0", "generation_seconds_batch": 17.467800884973258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.045135498046875, "target_z": 2.6875, "ce": 5.9431867599487305, "genuineness": 4.143336772918701, "identity": 0.5754145383834839, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/43212aff020a14d7d8adf5a55a649bec6d93e88b6fc933409267b11b4e125e39.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "f59a9de307e8c23dda058279534fabbf613abcc770cce5725b0fa85e217865e8", "generation_seconds_batch": 17.734599188086577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027523398399353027, "target_z": -0.617187493898272, "ce": 6.173524379730225, "genuineness": 4.337893962860107, "identity": 0.5757330060005188, "hypothesis": "De weg gaat linksaf na de brug. Loop verder tot aan het kleine Houten hek. Ik wacht aan de andere kant.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.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": "43530df4f1cacf427785b093ec60a337086c4c5a4142d4b69323a94be9b5a749", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e6255816d3fe6004231184dbb02f3b737df6695e7a37b58c738016929fc2833", "generation_seconds_batch": 15.41321358201094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.362599641084671, "target_z": -0.06835936737283999, "ce": 6.435632705688477, "genuineness": 4.65797233581543, "identity": 0.6709823608398438, "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_Pleasure_Ecstasy/43530df4f1cacf427785b093ec60a337086c4c5a4142d4b69323a94be9b5a749.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "dbc72dd909125be8194b4b16deff919faa340e649c12d83b3228f0e8e5838a84", "generation_seconds_batch": 15.463117914041504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5975107550621033, "target_z": 0.31640627745777605, "ce": 6.2767791748046875, "genuineness": 4.65797233581543, "identity": 0.6248526573181152, "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_Pleasure_Ecstasy/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "4433025657121017f530d714d8e2c3546edbd24acbea2f009124bbaaec8b53de", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e826be897c5342b771ea94af1ca8a7cca7cdc6fcc541b280a256dfa503abfd28", "generation_seconds_batch": 20.015093515976332, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13961294293403625, "target_z": -0.43359377135604804, "ce": 6.316492557525635, "genuineness": 4.6705241203308105, "identity": 0.5993019342422485, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4433025657121017f530d714d8e2c3546edbd24acbea2f009124bbaaec8b53de.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "444643269124affe4a6ef9b3f97bdfb46ef2461f73783b13eac71199662382ed", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "82c2c3a320062033b76f0aa244124fc6996da6e0b8305d6c62103d947cc3dd25", "generation_seconds_batch": 22.112029579933733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7262945175170898, "target_z": 0.5273437957629601, "ce": 6.467403411865234, "genuineness": 4.306513786315918, "identity": 0.31161195039749146, "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_Pleasure_Ecstasy/444643269124affe4a6ef9b3f97bdfb46ef2461f73783b13eac71199662382ed.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "446e8c81c008a2d941ca361acd06777bce321d41dded9abde5edcf51c1387938", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4057402fabbb26fb5b090e355cdd0ccbadbc603c6291c7e83236148d918d81d7", "generation_seconds_batch": 19.667258245055564, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8448052406311035, "target_z": 2.359375036610368, "ce": 6.205295085906982, "genuineness": 4.306513786315918, "identity": 0.5677023530006409, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/446e8c81c008a2d941ca361acd06777bce321d41dded9abde5edcf51c1387938.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "44e9c88f14a695d620d2403d200b5c85a924176d3957e96f5a2d775a8f556a06", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fd2163838c6930510e9615b70978a8b5e0c91dae3d6d5c5af603cf6c4d5f987a", "generation_seconds_batch": 20.497823300072923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9099305868148804, "target_z": 0.828125012203456, "ce": 6.133810997009277, "genuineness": 4.362998008728027, "identity": 0.6401267051696777, "hypothesis": "La porte 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_Pleasure_Ecstasy/44e9c88f14a695d620d2403d200b5c85a924176d3957e96f5a2d775a8f556a06.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "44f39d859e7b4e2ca71c422ada38b25675b3cfeb3c62cc0f6953ce868096d2d8", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b43c3caa9a621d6da4989ff233fafef03a5518c9b280fb63ebc581af77d910ff", "generation_seconds_batch": 19.334609408979304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1198004484176636, "target_z": 1.1718750854241922, "ce": 6.229123115539551, "genuineness": 4.406930446624756, "identity": 0.4036243259906769, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/44f39d859e7b4e2ca71c422ada38b25675b3cfeb3c62cc0f6953ce868096d2d8.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "456222a60fe6bacadf087436e8ccc96f540dcf15f08f60507a1c43edf65d5fe9", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "5f416ce27f0b9f551597e4e6bc919ba79ed42eb3c258b03d63dd13795cdc7e8e", "generation_seconds_batch": 21.5707573259715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.367828369140625, "target_z": 1.578125012203456, "ce": 6.300607204437256, "genuineness": 4.532451152801514, "identity": 0.6357665061950684, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/456222a60fe6bacadf087436e8ccc96f540dcf15f08f60507a1c43edf65d5fe9.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "456e7f6bbec34ce1d5357c63c529d29077caf36107b636ced77dba5605c8f60f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1ed3f7ca0d1d8fbcef66a8a24f38cab714acd342ce019b627f6340d22f4fb387", "generation_seconds_batch": 18.007951783947647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.720791220664978, "target_z": 2.156249975593088, "ce": 6.1894097328186035, "genuineness": 4.306513786315918, "identity": 0.5741735696792603, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/456e7f6bbec34ce1d5357c63c529d29077caf36107b636ced77dba5605c8f60f.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": "456fe5876e59737ae488aa063af552742bd3dc4b19f4dbe7fa66b6c6b00f944d", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71b104f0fbe6d21ede74adefe6413c11dfa4ab3afbadd0ae6127fc02b275571d", "generation_seconds_batch": 16.209773445967585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18850308656692505, "target_z": -0.353515620423704, "ce": 6.4515180587768555, "genuineness": 3.9425034523010254, "identity": 0.34660735726356506, "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_Pleasure_Ecstasy/456fe5876e59737ae488aa063af552742bd3dc4b19f4dbe7fa66b6c6b00f944d.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "457d141da058b0b69b594af75a99266fb8329aa8cc80d591b3aa9eb1b7e86630", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "67bd9b3648ae8ef941e15dd8f5991ac4fc320d1671e0b59129fbdb1a658b2398", "generation_seconds_batch": 20.219445734051988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8288445472717285, "target_z": 0.6953125549155521, "ce": 6.23706579208374, "genuineness": 4.482243061065674, "identity": 0.6171392202377319, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/457d141da058b0b69b594af75a99266fb8329aa8cc80d591b3aa9eb1b7e86630.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "45e1f9a1d61f7c8de8d42a0a53eafdb4514b111c339553094bdc5d28776b0341", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "31d2459cbbfdf23a944f10ab6a7cfb61279b6b800dd1b661ac5a0b76612010ba", "generation_seconds_batch": 20.88050187099725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.367828369140625, "target_z": 1.578125012203456, "ce": 6.078212261199951, "genuineness": 4.20609712600708, "identity": 0.6493325233459473, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/45e1f9a1d61f7c8de8d42a0a53eafdb4514b111c339553094bdc5d28776b0341.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "b2b173f3c80bcd709c4cca5c289f0671094abea192a401d594ba55d635467475", "generation_seconds_batch": 16.15650696400553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.044217586517333984, "target_z": -0.589843746949136, "ce": 6.348263263702393, "genuineness": 4.306513786315918, "identity": 0.523030161857605, "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_Pleasure_Ecstasy/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "45fd7b82f9902729b1a49cea82a425767cc5f3a0ae5c5de5d437b76a7b0afcef", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d5309b35fcc16cc0057accf61bcc73bdeabc41cd6960bac588da90b5e6c7e5ce", "generation_seconds_batch": 21.171675069024786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5204609632492065, "target_z": 1.828125012203456, "ce": 6.348263263702393, "genuineness": 4.444586753845215, "identity": 0.487632691860199, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/45fd7b82f9902729b1a49cea82a425767cc5f3a0ae5c5de5d437b76a7b0afcef.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "4604745074bc222e00d555738c8d796b150df8dc953bcd55d206664e3b77d446", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "253f2fbea12d0adbe531cee6e68bcd00c80053c1f95680f56bbd0456e2c745cc", "generation_seconds_batch": 20.544263600022532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8097654581069946, "target_z": 0.6640625305086401, "ce": 6.0305562019348145, "genuineness": 4.105680465698242, "identity": 0.3564904034137726, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4604745074bc222e00d555738c8d796b150df8dc953bcd55d206664e3b77d446.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "467179676533d39e0f71fe455476520c815538d7ac83375fca36d9129727edd1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8988ed3e162baa73e1bedf99b84405566e9259da719eaa61c6110d973b405c0a", "generation_seconds_batch": 21.31712391495239, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47140997648239136, "target_z": 0.10986327247876598, "ce": 6.41180419921875, "genuineness": 4.005263805389404, "identity": 0.47171589732170105, "hypothesis": "The 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_Pleasure_Ecstasy/467179676533d39e0f71fe455476520c815538d7ac83375fca36d9129727edd1.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "473c812fcb31e5359bc3b8537a6096f23b21c100cb6a0cd8305b4e85474da625", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "24dba1da770b334b325b9afc60238c3865df7ee13d590cab5b0b6ab170b99073", "generation_seconds_batch": 16.457519276998937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6666723489761353, "target_z": 0.4296874450844479, "ce": 6.38003396987915, "genuineness": 4.632867813110352, "identity": 0.5662097334861755, "hypothesis": "De deur 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_Pleasure_Ecstasy/473c812fcb31e5359bc3b8537a6096f23b21c100cb6a0cd8305b4e85474da625.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "474e90546f5b3c7167cd7452d0da0b5ff0575e758c04f0e420227e7403af853d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "923806d553663f63f487ee0145769eda3dd1fef6990f473b2ab0a186d5e0472d", "generation_seconds_batch": 17.44420046498999, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4679934978485107, "target_z": 1.742187493898272, "ce": 6.260893821716309, "genuineness": 4.168440818786621, "identity": 0.5932119488716125, "hypothesis": "J'ai trouvé la deux petites boîtes. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/474e90546f5b3c7167cd7452d0da0b5ff0575e758c04f0e420227e7403af853d.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": "47c22a8bdf2b7dabd01368ef6bf62e6799a9808ee1ee2ac7ff515746cd33ee1d", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cb35394820d2d5b390b8fd9aa408b09dfe4b94bf983b2889ed79d886e54f65c1", "generation_seconds_batch": 24.316788019961677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7572979927062988, "target_z": 0.578125012203456, "ce": 6.316492557525635, "genuineness": 4.356721878051758, "identity": 0.7108852863311768, "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_Pleasure_Ecstasy/47c22a8bdf2b7dabd01368ef6bf62e6799a9808ee1ee2ac7ff515746cd33ee1d.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "7ecdc14e75b67faba835b8af2f65ba04f80a15ff801518726ce8653c05bca2f3", "generation_seconds_batch": 15.250068085966632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11576411128044128, "target_z": -0.472656253050864, "ce": 6.141753673553467, "genuineness": 4.758388519287109, "identity": 0.8337830305099487, "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_Pleasure_Ecstasy/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "484d72215dcf8b09ba1e5233b6477a6d246e412b61a5719eeab90bace403038f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cc2a84d2f45320da3602b2b3fbf57ffb644410267409cc2c7c99b1f9f62653aa", "generation_seconds_batch": 20.263288798974827, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2797248959541321, "target_z": -0.20410158156790004, "ce": 6.316492557525635, "genuineness": 4.13078498840332, "identity": 0.3331759572029114, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/484d72215dcf8b09ba1e5233b6477a6d246e412b61a5719eeab90bace403038f.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "487b7235f77ba470d1a44b7bb55f36f842c1d685a2d3483b9c99ef7687a443db", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "23017ef38d6eb831aa4112ca1612d96294d4f20aff3e5afaa6775d5ceab59e6c", "generation_seconds_batch": 20.497823300072923, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7954561710357666, "target_z": 0.6406250610172801, "ce": 6.109982967376709, "genuineness": 4.356721878051758, "identity": 0.6907079219818115, "hypothesis": "La porte 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_Pleasure_Ecstasy/487b7235f77ba470d1a44b7bb55f36f842c1d685a2d3483b9c99ef7687a443db.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "48f93648482e53c80c76fddcf21bea35839cbe02e500e55416a4f72702133070", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4c3ddba6c2cd1ad5e7519825bb13fbbadf6c42600c8757016f9d43fd00424080", "generation_seconds_batch": 23.155982555937953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0100957155227661, "target_z": 0.992187493898272, "ce": 6.2767791748046875, "genuineness": 3.9299514293670654, "identity": 0.4235233664512634, "hypothesis": "The 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_Pleasure_Ecstasy/48f93648482e53c80c76fddcf21bea35839cbe02e500e55416a4f72702133070.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "491addce1c3d0bb4c07d6f74e966e8893f855758b2955ce92f0e0198db989779", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "443e1e21e783cf0f2f666cb4b6d4808f5abf1d0e9115656052b526b60c606f98", "generation_seconds_batch": 19.37193110701628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7930712699890137, "target_z": 0.6367187835595041, "ce": 6.284721851348877, "genuineness": 4.337893962860107, "identity": 0.33893445134162903, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/491addce1c3d0bb4c07d6f74e966e8893f855758b2955ce92f0e0198db989779.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "4951adf4783f6aca136a43d22d83cd9725c3e12f78d06b426af1dd51100fde6d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b7f1aa77a003c351c88d6f170ce7f1d7e2196b429233fbb17962541c8fb5591c", "generation_seconds_batch": 20.64067047496792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7477584481239319, "target_z": 0.5625, "ce": 6.173524379730225, "genuineness": 4.582659721374512, "identity": 0.3316701650619507, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4951adf4783f6aca136a43d22d83cd9725c3e12f78d06b426af1dd51100fde6d.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": "49805846a50f1f0064f7ef65f07366059e79b595a7f5f855df001bda7d9825df", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ce04f9f2b84e842ffa2e22b065280b5991ce946cee969ffe23bacdd137a50331", "generation_seconds_batch": 21.6009789040545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.711985170841217, "target_z": 0.503906228643952, "ce": 6.284721851348877, "genuineness": 4.268857479095459, "identity": 0.48057252168655396, "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_Pleasure_Ecstasy/49805846a50f1f0064f7ef65f07366059e79b595a7f5f855df001bda7d9825df.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "695493c26ecc39123c299c97d01eb59621c151f8a84f6a9d31731ca4e4d7426e", "generation_seconds_batch": 15.261996690067463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5194057822227478, "target_z": 0.188476569364444, "ce": 6.173524379730225, "genuineness": 4.250029563903809, "identity": 0.6011061668395996, "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_Pleasure_Ecstasy/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "4a3fcf1072511480b165d10aa6faa7dc1381d0a6ac9e25255e5178d26d5a824f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "827f9f14b2dfb47b8384c6b2eaf19589fa775cbf94c6aa9dcf5ac75c4467a2c0", "generation_seconds_batch": 20.111330024898052, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4441447257995605, "target_z": 1.7031251098311042, "ce": 6.213237762451172, "genuineness": 4.482243061065674, "identity": 0.761610746383667, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4a3fcf1072511480b165d10aa6faa7dc1381d0a6ac9e25255e5178d26d5a824f.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "4a6e3bdfff9368ab40c98c7cf695d727d598a63290a5db95916a8095565c7025", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ed655c093a162ed8cb01910bc5c850bd9b2a887d50e9b45c21b221d55fee58ef", "generation_seconds_batch": 21.31712391495239, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3983728885650635, "target_z": -0.009765644830616031, "ce": 6.221180438995361, "genuineness": 3.7793264389038086, "identity": 0.34509706497192383, "hypothesis": "The 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_Pleasure_Ecstasy/4a6e3bdfff9368ab40c98c7cf695d727d598a63290a5db95916a8095565c7025.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "4a93f249fa07ba7afbe047cad905565da98c35c92257527178bb8ce6a3735a59", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4aa5d0dcdb954f3452707b831d2a431bd38eef21ca543d1cfc460ebe507e965d", "generation_seconds_batch": 20.731884787091985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2438143491744995, "target_z": 1.374999951186176, "ce": 6.046441555023193, "genuineness": 4.337893962860107, "identity": 0.4343453049659729, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4a93f249fa07ba7afbe047cad905565da98c35c92257527178bb8ce6a3735a59.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "4ace3228fc91151dc84a8b09f1649ef649ed9408646fd899de3b1c9657a36ef6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "821c96877785eb343200056887cf26e127401675fbb10cdb77977e96baedc8c3", "generation_seconds_batch": 20.660620426991954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7692223787307739, "target_z": 0.5976562042370399, "ce": 6.316492557525635, "genuineness": 4.293961524963379, "identity": 0.2326185554265976, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4ace3228fc91151dc84a8b09f1649ef649ed9408646fd899de3b1c9657a36ef6.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": "4b72c65e6a906305cf4bbcd33739c7a26a93729c23f5fd1a2808453e41545cc7", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa5aab07792c53117d3cdc85918028d84ca790a7b3011d387db16a464d431ab4", "generation_seconds_batch": 24.45478479808662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7084078788757324, "target_z": 0.49804691008493607, "ce": 6.149696350097656, "genuineness": 4.494794845581055, "identity": 0.8777116537094116, "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_Pleasure_Ecstasy/4b72c65e6a906305cf4bbcd33739c7a26a93729c23f5fd1a2808453e41545cc7.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "4bd679824fb6a789515cc05519935c1337c76f5a28fddad47e7d3952f96acae2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b8a5cf09cf8d4932a1984acd7495ba173fecc6270abc407c84ae2b5b821adc6a", "generation_seconds_batch": 21.11558313795831, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9075456857681274, "target_z": 0.82421873474568, "ce": 6.086154937744141, "genuineness": 4.3127899169921875, "identity": 0.06470021605491638, "hypothesis": "De deur 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_Pleasure_Ecstasy/4bd679824fb6a789515cc05519935c1337c76f5a28fddad47e7d3952f96acae2.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "4c80097a152c369fafab2a433031ead49b8ef8fa30f5ba9a2d26289157c1c36d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "793249018d04e48ad80953162dca8ea31d0889e1aedb16a9d6a221b5be0b7df0", "generation_seconds_batch": 17.507333416957408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09668505191802979, "target_z": -0.503906228643952, "ce": 6.141753673553467, "genuineness": 4.432034492492676, "identity": 0.4447224736213684, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4c80097a152c369fafab2a433031ead49b8ef8fa30f5ba9a2d26289157c1c36d.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "4cbdc870d1c804a69349fcae5a4fd64d3ee12ff1738f749d0c78b2dd0f9a738f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f15f89bce6c0715410c11a8b275b26bbf3a80d23695dffe47074a29b72284cf1", "generation_seconds_batch": 22.912547313026153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5156911611557007, "target_z": 1.820312457287904, "ce": 5.927301406860352, "genuineness": 3.998987913131714, "identity": 0.06794833391904831, "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_Pleasure_Ecstasy/4cbdc870d1c804a69349fcae5a4fd64d3ee12ff1738f749d0c78b2dd0f9a738f.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "4cfa0d55d55140012d3477b16a6ca61e472a4bb5307f5ef5e96a15980aa29ba6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "dc5971b97012c42434b4d2fff3ee64788f8beec3eec1aa318fdceb7855876b5e", "generation_seconds_batch": 15.172261693980545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4298354387283325, "target_z": 1.6796876403397443, "ce": 6.252951145172119, "genuineness": 4.017816066741943, "identity": 0.38934630155563354, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4cfa0d55d55140012d3477b16a6ca61e472a4bb5307f5ef5e96a15980aa29ba6.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": "4d6c45f35de53c9da984d0624c94ad93bce610d75fd3af4ce31ddb5e90a63461", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00e5816f6353a1b93cdf6720736a598101be67a7baf75446c4eade0b92e574de", "generation_seconds_batch": 20.611456669983454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23739321529865265, "target_z": -0.273437493898272, "ce": 6.197352409362793, "genuineness": 4.256305694580078, "identity": 0.7445704936981201, "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_Pleasure_Ecstasy/4d6c45f35de53c9da984d0624c94ad93bce610d75fd3af4ce31ddb5e90a63461.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "4d9276b7f6e01f45f7c5ba8bfadc041775058f0f84296ba328bd192b7b110c16", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "100a241ef63cc0a016c0b5c724b1b66f82c3b1eb0b8d004631ac8f6eb1b709b6", "generation_seconds_batch": 22.29504352598451, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2199655771255493, "target_z": 1.3359375671190081, "ce": 6.24500846862793, "genuineness": 4.256305694580078, "identity": 0.35671353340148926, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4d9276b7f6e01f45f7c5ba8bfadc041775058f0f84296ba328bd192b7b110c16.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "4d9433e6c8ebdc111223cd643e57c1d310942fef49a357d2b63738b5d13f98fc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "beb5782e42c5fffc7bec2b378b8b54b2e59536303f9bd70f3115c557b74858f8", "generation_seconds_batch": 20.501100067049265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07999083399772644, "target_z": -0.531250024406912, "ce": 6.197352409362793, "genuineness": 4.20609712600708, "identity": 0.7240778803825378, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4d9433e6c8ebdc111223cd643e57c1d310942fef49a357d2b63738b5d13f98fc.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "4dc4f53f55e028812eea5d62ce8ac6b3f97d3746dedc20d2795c2456f11cdbe5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9a0efaa663146016d6b371960659e43171beb58141eb92ab7ddcee2b5fe4c68e", "generation_seconds_batch": 22.224279579007998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8073805570602417, "target_z": 0.660156253050864, "ce": 6.324435234069824, "genuineness": 4.532451152801514, "identity": 0.6897459030151367, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4dc4f53f55e028812eea5d62ce8ac6b3f97d3746dedc20d2795c2456f11cdbe5.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "4dcb9d17f28bbed1cb12361a75807a28f1c21070ecfe9a37487bedd205b4501f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fcdb723c095f565668554bf637fe200fb32f5ff1073195c2fc3d8821ee32687d", "generation_seconds_batch": 19.64325412805192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49019095301628113, "target_z": 0.14062501220345602, "ce": 6.221180438995361, "genuineness": 4.519899368286133, "identity": 0.47772008180618286, "hypothesis": "La porte 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_Pleasure_Ecstasy/4dcb9d17f28bbed1cb12361a75807a28f1c21070ecfe9a37487bedd205b4501f.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "4e2cc0dd58512b6a4f35085dd69e0835d92d34661d60365e3a20c3abb1d2f0dc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5e4e77e7bae2b9b1a855523a3c6ae927b813874c6b6e43dc4bd92ae78dcc22f6", "generation_seconds_batch": 20.657300467020832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32086417078971863, "target_z": -0.13671873474567997, "ce": 6.062326908111572, "genuineness": 4.570107460021973, "identity": 0.5662802457809448, "hypothesis": "La porte 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_Pleasure_Ecstasy/4e2cc0dd58512b6a4f35085dd69e0835d92d34661d60365e3a20c3abb1d2f0dc.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "4e45c051065fb1491942aad3cc9488b6adcabfa7fa8c8a66f577132196cd5ae2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e3ac5a6dfd885a9c57969b2ee405d99e4fbd805eea2af651dd76bb3dac8e87ae", "generation_seconds_batch": 21.428235108032823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.020368754863739014, "target_z": -0.628906228643952, "ce": 5.967014789581299, "genuineness": 4.444586753845215, "identity": 0.6601792573928833, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4e45c051065fb1491942aad3cc9488b6adcabfa7fa8c8a66f577132196cd5ae2.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "4f0cdc44a6524096a25308b4d24543bfa4a48c7d8800c73c05cfef13d6651e2c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ff7982695b5a0e89ad0367fa2d890eda249bb102d403d9953992d4c3f446f0ab", "generation_seconds_batch": 22.912547313026153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2438143491744995, "target_z": 1.374999951186176, "ce": 6.300607204437256, "genuineness": 4.18099308013916, "identity": 0.11303780972957611, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4f0cdc44a6524096a25308b4d24543bfa4a48c7d8800c73c05cfef13d6651e2c.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": "4f0d4b8ce1b820cd384b00e012e350098a06304aca2c49996e0823a89a6bf909", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e9e19d98872de6f6f5b8fc6e186ce9b9f9e2e91354a0bd18ed532bbd3e010c66", "generation_seconds_batch": 23.549209037912078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3775051534175873, "target_z": -0.043945328517036024, "ce": 6.419747352600098, "genuineness": 4.394378662109375, "identity": 0.4275427460670471, "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_Pleasure_Ecstasy/4f0d4b8ce1b820cd384b00e012e350098a06304aca2c49996e0823a89a6bf909.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "4f34b1d038acc1fb2fe2c2140ae6c703f9585f33e039a8e495d3787f2094ba61", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b9bffa3f4a1b229ca4600bfb57d05ee9ad2860f119393c97c8b2149511b963cc", "generation_seconds_batch": 19.32586746197194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9790922403335571, "target_z": 0.941406277457776, "ce": 6.070269584655762, "genuineness": 4.457139015197754, "identity": 0.5704693794250488, "hypothesis": "La porte 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_Pleasure_Ecstasy/4f34b1d038acc1fb2fe2c2140ae6c703f9585f33e039a8e495d3787f2094ba61.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": "4f8cc2e844c0061c544a2126831370fdab281ec8ba0c3b9c04d84ec5788a7aea", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b518beb7146fe8507f93e1a04a797911e14a2b9755c128fdd5d0febd1cd8d55", "generation_seconds_batch": 23.71434092510026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9290096759796143, "target_z": 0.8593750366103681, "ce": 6.197352409362793, "genuineness": 4.356721878051758, "identity": 0.7274806499481201, "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_Pleasure_Ecstasy/4f8cc2e844c0061c544a2126831370fdab281ec8ba0c3b9c04d84ec5788a7aea.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "4fa173e11e4f2ba66cb9b10800803d85243b74847a1cde06e1ff96644c92fd07", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0ea5be6fdcacab03400362157e889146a37ebdaad9828164d7411e5e330ac074", "generation_seconds_batch": 21.593442999990657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.692172646522522, "target_z": 2.109375036610368, "ce": 6.181467056274414, "genuineness": 4.469690799713135, "identity": 0.6414878368377686, "hypothesis": "La porte 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_Pleasure_Ecstasy/4fa173e11e4f2ba66cb9b10800803d85243b74847a1cde06e1ff96644c92fd07.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "4fa3f3bca0d4b98bcc4c7a32f0a9946ed50280d84b0c7b67dcaa58c649471588", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f30300e28f63dfd70604e8ccd07b6f52655e47f18d0ea04a5697c5df2f1f036f", "generation_seconds_batch": 15.193860337953083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0260562896728516, "target_z": 2.6562497803377916, "ce": 6.046441555023193, "genuineness": 4.15588903427124, "identity": 0.5896931290626526, "hypothesis": "The 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_Pleasure_Ecstasy/4fa3f3bca0d4b98bcc4c7a32f0a9946ed50280d84b0c7b67dcaa58c649471588.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "4fc76f9cfd4e8d8c94c9a6daa909291e8ce4227a4028a32724f58731b2676bf2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "83c088739a197fcbd4f6e17567e17923be31069d58924a801165e9c129566a62", "generation_seconds_batch": 19.80245630000718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2724330425262451, "target_z": 1.4218750854241922, "ce": 5.788304805755615, "genuineness": 3.810706615447998, "identity": 0.36932963132858276, "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_Pleasure_Ecstasy/4fc76f9cfd4e8d8c94c9a6daa909291e8ce4227a4028a32724f58731b2676bf2.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "4fee202cdedfa88ff7097fd21928379d61aaaa1408cb9da3cebc4331dc8ca24b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a8be0792c8b9122c7dfb27a9862e7d0d6bcccca120c4776d544201c83901a6d3", "generation_seconds_batch": 16.27537918300368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0069773197174072, "target_z": 2.624999951186176, "ce": 6.0305562019348145, "genuineness": 4.243753433227539, "identity": 0.4767405390739441, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/4fee202cdedfa88ff7097fd21928379d61aaaa1408cb9da3cebc4331dc8ca24b.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "50acb30b2e61bcd7add1a3dd74fac3b17df2ef699d31df4719126e293141c4cd", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "02d300ff168fc277d026153690c9271d81ee5580f89d98c95ca910b9831c0a43", "generation_seconds_batch": 22.54853291006293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.697675883769989, "target_z": 0.480468759152592, "ce": 6.348263263702393, "genuineness": 4.024092197418213, "identity": 0.37527352571487427, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/50acb30b2e61bcd7add1a3dd74fac3b17df2ef699d31df4719126e293141c4cd.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "526036cd9520f2f430a3933680b0bbbed73551cd0b7b2f3cac73570e679fe795", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "71ab7f14df16aadca9f4bad770ae8511a20ce69c8bf11cb265f551a26fe597ab", "generation_seconds_batch": 19.89433935494162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9719375371932983, "target_z": 0.9296874450844479, "ce": 6.197352409362793, "genuineness": 4.400654315948486, "identity": 0.7072577476501465, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/526036cd9520f2f430a3933680b0bbbed73551cd0b7b2f3cac73570e679fe795.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "5278c00b55dcbebc45ee5860c3a48a493c7d65455e7b3dc477c13d1c40786dbf", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8262da8548d1a207de250afa083730e4759ef0d7d63caf6f671ff5c5b5cd5c06", "generation_seconds_batch": 19.551575660938397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2199655771255493, "target_z": 1.3359375671190081, "ce": 6.221180438995361, "genuineness": 4.1998209953308105, "identity": 0.3971560001373291, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5278c00b55dcbebc45ee5860c3a48a493c7d65455e7b3dc477c13d1c40786dbf.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": "528b8965a40bab33471ce3ea40df2d6848bc448402a6354fd847a3811f840e1e", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c2a6e5cc3c0ab8bd294539d964d9cf3ca070a20485a4e776d32b3660affced68", "generation_seconds_batch": 16.12436462601181, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4035898447036743, "target_z": -0.0012206872986429756, "ce": 6.4515180587768555, "genuineness": 4.570107460021973, "identity": 0.6398960947990417, "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_Pleasure_Ecstasy/528b8965a40bab33471ce3ea40df2d6848bc448402a6354fd847a3811f840e1e.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "529546752491f8a7a56e044ebb6534fbf6b100d8f7661f5938257431dd2a63d9", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3bbb27c67c868e2d903355f03f49bdbf44c2e685734f95d8b776bf2abb74b40e", "generation_seconds_batch": 20.511945129022934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5665072202682495, "target_z": 0.26562496338963193, "ce": 6.149696350097656, "genuineness": 4.507347106933594, "identity": 0.7097181677818298, "hypothesis": "La porte 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_Pleasure_Ecstasy/529546752491f8a7a56e044ebb6534fbf6b100d8f7661f5938257431dd2a63d9.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": "5302f0a06015c0aacc09d0c0c30f66dca27b12166aac59b472d4d39feca36e23", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2201cb7a1ecb61adc64abd8a58dccc204d0beb90a90f678546a33494bf6f3333", "generation_seconds_batch": 16.522469925927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7382189035415649, "target_z": 0.546874987796544, "ce": 6.221180438995361, "genuineness": 4.406930446624756, "identity": 0.6208346486091614, "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_Pleasure_Ecstasy/5302f0a06015c0aacc09d0c0c30f66dca27b12166aac59b472d4d39feca36e23.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "530885ea5991ac654f28e7937f66a8dc163013c7f42dd05a8b3cdec59c5578db", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6f14f5b7b5c973a873a571deb062bbb7555e9bd44f30723ed5f05a81004e1da0", "generation_seconds_batch": 20.302951619029045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8543447256088257, "target_z": 2.374999951186176, "ce": 5.895530700683594, "genuineness": 4.381826400756836, "identity": 0.6641455888748169, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/530885ea5991ac654f28e7937f66a8dc163013c7f42dd05a8b3cdec59c5578db.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "5312985e099f6ea30cfca4f2058166ea2f8ea73224a1ba6d8620b1d5941ab355", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "97e446d3e690d84a6f0f94f2e8db44e5f55cc3661ccf3ad0f5366af492b28aec", "generation_seconds_batch": 15.602854548022151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5253679752349854, "target_z": 0.19824216538123596, "ce": 6.419747352600098, "genuineness": 4.231201171875, "identity": 0.2889890968799591, "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_Pleasure_Ecstasy/5312985e099f6ea30cfca4f2058166ea2f8ea73224a1ba6d8620b1d5941ab355.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "532daba0ed98de4b0e8bd97aba6c022b76e695570b8cc83640c7ddd1deb908a8", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4acc2279058a41a65872f4abb39afd13f7748030395bd48d100afab417167801", "generation_seconds_batch": 19.63146003196016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2390446662902832, "target_z": 1.3671875915259202, "ce": 6.141753673553467, "genuineness": 4.143336772918701, "identity": 0.3811717629432678, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/532daba0ed98de4b0e8bd97aba6c022b76e695570b8cc83640c7ddd1deb908a8.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": "535e7fce3e258375475db7ad92d352526d24ad8687226fdcfdec08a83c16cc64", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1eccec5680e268e32753685385fce7452cac561196f6f1079e4dbf143e5ef96e", "generation_seconds_batch": 17.87501128797885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29522666335105896, "target_z": -0.17871092453382798, "ce": 6.340320587158203, "genuineness": 4.356721878051758, "identity": 0.768584132194519, "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_Pleasure_Ecstasy/535e7fce3e258375475db7ad92d352526d24ad8687226fdcfdec08a83c16cc64.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "539d8efd02d09e9b20b944880b01fa55f7d813c6acef4337a98a4eafb47d5727", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7589eff7fc4eeb75ad06356bf5ea648514006646f642e2614e1b802a7afa455c", "generation_seconds_batch": 20.10203339299187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7310642600059509, "target_z": 0.535156253050864, "ce": 6.23706579208374, "genuineness": 4.337893962860107, "identity": 0.5303853750228882, "hypothesis": "De deur 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_Pleasure_Ecstasy/539d8efd02d09e9b20b944880b01fa55f7d813c6acef4337a98a4eafb47d5727.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "53d951dd8e999687e0586e7467f33f30bb0588f9ead4b383c3440b3a6b8c1ad9", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c5ef8064e986af07db92ef6349b494d01a08024c1e0154404d48de7d62c9daf7", "generation_seconds_batch": 20.660620426991954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41715386509895325, "target_z": 0.020996094894074002, "ce": 6.252951145172119, "genuineness": 4.557555198669434, "identity": 0.3913668990135193, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/53d951dd8e999687e0586e7467f33f30bb0588f9ead4b383c3440b3a6b8c1ad9.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": "540966987c0ebf97edd202471d5166f790fe0e883d6f9e46a571b70b07c7c4f9", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d2950939b9eb6db8b93de7f90815a896207ad2a3e785e6447bc4415b21721582", "generation_seconds_batch": 17.876762942993082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1372280716896057, "target_z": -0.4375, "ce": 6.395919322967529, "genuineness": 4.15588903427124, "identity": 0.4857289493083954, "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_Pleasure_Ecstasy/540966987c0ebf97edd202471d5166f790fe0e883d6f9e46a571b70b07c7c4f9.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "540ea6c067a36ec0fa600807c96c40ea688296067f5fb0fb6bf475eda1f94681", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "039020c1e3eb42d2fb2f99d44e6b739bf0a97ec9b78b072060e0327b3bc3c614", "generation_seconds_batch": 16.552942053996958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0959515571594238, "target_z": 1.132812506101728, "ce": 6.252951145172119, "genuineness": 4.306513786315918, "identity": 0.6295369863510132, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/540ea6c067a36ec0fa600807c96c40ea688296067f5fb0fb6bf475eda1f94681.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "54131e380d78433f6d2254b85ad86011f5761d12e365c722268e3f3aac0d9b51", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4c40b9621cfb1ada58cf0c0b122d406f1862e60798673c4eab043eb699ef5a7e", "generation_seconds_batch": 17.69778294104617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.983862042427063, "target_z": 0.9492188323733282, "ce": 6.284721851348877, "genuineness": 4.262581825256348, "identity": 0.717199444770813, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/54131e380d78433f6d2254b85ad86011f5761d12e365c722268e3f3aac0d9b51.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "5438659c89650c635e5ab86b6bdce4e1750f024df609b04e55a2c0aedb920303", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "289cfc320c05657dc33db02a433637480f7a9466a29c418656f3454445ebcfa8", "generation_seconds_batch": 15.82911921502091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9504736661911011, "target_z": 0.8945313384750562, "ce": 6.340320587158203, "genuineness": 4.457139015197754, "identity": 0.35795050859451294, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5438659c89650c635e5ab86b6bdce4e1750f024df609b04e55a2c0aedb920303.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "5461d1581b6d382d10105ca68821d793d210fde3308638a7c83cd952d5095ef5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b9fa9d27d4821e41d08600da6eae91b32c2ffbcb019a1232a472356717145fac", "generation_seconds_batch": 20.839750748942606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8066470623016357, "target_z": 2.296874987796544, "ce": 6.292664527893066, "genuineness": 4.570107460021973, "identity": 0.5549747943878174, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5461d1581b6d382d10105ca68821d793d210fde3308638a7c83cd952d5095ef5.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "bd12f73d5716193d1913ea5fdd8e02c064b6b4dfd482f76f317479bfcaf6f664", "generation_seconds_batch": 16.15650696400553, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.027523398399353027, "target_z": -0.617187493898272, "ce": 6.284721851348877, "genuineness": 4.049196243286133, "identity": 0.7554836273193359, "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_Pleasure_Ecstasy/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "54b836d7310d3ee4b2fc5321b983e359f709955106b893d1ad915bf0432e0bbc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0df3ecdff4493c9d93274c804c5869127502acbc29d1b3a15a08e96400cc4b04", "generation_seconds_batch": 20.016108470968902, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3465016782283783, "target_z": -0.09472654495753197, "ce": 5.967014789581299, "genuineness": 4.331617832183838, "identity": 0.6013391017913818, "hypothesis": "La porte 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_Pleasure_Ecstasy/54b836d7310d3ee4b2fc5321b983e359f709955106b893d1ad915bf0432e0bbc.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "54b8da31a1709cbb612295c0ef41ae7b142acc377ec38fd12b9d4787c462988e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "412d1b6e54f2de10314c3729c0362d2be07b08031e08486df077ccfc00553486", "generation_seconds_batch": 21.362324477988295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2642231583595276, "target_z": -0.229492189788148, "ce": 6.181467056274414, "genuineness": 4.21237325668335, "identity": 0.6433428525924683, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/54b8da31a1709cbb612295c0ef41ae7b142acc377ec38fd12b9d4787c462988e.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "54d3538b15831f1c1e37beb9c6ec9c9cb735ab15a68ccc9e323ee31045746738", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9dd47e92b1edf78d8d6cb6be8ed99315d2f1bfbbbfddd291242a975ca575ccc1", "generation_seconds_batch": 15.193860337953083, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6015470027923584, "target_z": 1.96093746949136, "ce": 6.046441555023193, "genuineness": 3.7667744159698486, "identity": 0.20689202845096588, "hypothesis": "The 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_Pleasure_Ecstasy/54d3538b15831f1c1e37beb9c6ec9c9cb735ab15a68ccc9e323ee31045746738.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "54d394e528166c2cafeba1474990ce9eb353a4722bfba2981509af3ee120fc05", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "098fabf07c6c8b89265b039caf239d3963e36837c6deebb84b1442fc9b2e755c", "generation_seconds_batch": 20.380356651963666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1491524875164032, "target_z": -0.417968759152592, "ce": 6.260893821716309, "genuineness": 4.457139015197754, "identity": 0.6119278073310852, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/54d394e528166c2cafeba1474990ce9eb353a4722bfba2981509af3ee120fc05.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "551c55c1042d877945aa381b51c4d080e2102adf248daf7240a47760d01457b7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "eb3f1f51462c8fd0709f0db29a6e072cff053d03a5711a5a1bc84a84df520152", "generation_seconds_batch": 20.83202970691491, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7017122507095337, "target_z": 2.1250001464414723, "ce": 5.927301406860352, "genuineness": 4.482243061065674, "identity": 0.3845213055610657, "hypothesis": "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_Pleasure_Ecstasy/551c55c1042d877945aa381b51c4d080e2102adf248daf7240a47760d01457b7.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "555c351acdc1e212210b4b65f7e3c6ce668bd251c2b7a701e3ae1a62af1cbf35", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6d8f842cfbe10e5a798fd66bbba63b1ee89d009987d4e1a473152677983df614", "generation_seconds_batch": 14.64427795400843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8161866664886475, "target_z": 2.312500097627648, "ce": 5.895530700683594, "genuineness": 4.557555198669434, "identity": 0.26951533555984497, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/555c351acdc1e212210b4b65f7e3c6ce668bd251c2b7a701e3ae1a62af1cbf35.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "559a1d3c874a9eeda4d49cc9415e5e95712301841133d3199727b2b5db8df6a5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "48d21594b5f7e3b6eed093cb70cd7525ddffdef0edaa85f8cf9f987419fe367f", "generation_seconds_batch": 17.32915079407394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5194057822227478, "target_z": 0.188476569364444, "ce": 6.141753673553467, "genuineness": 4.074300289154053, "identity": 0.5934999585151672, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/559a1d3c874a9eeda4d49cc9415e5e95712301841133d3199727b2b5db8df6a5.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "55c4992c8a2c55d81f6302c44bda9930ba493e8788417348e295a65533426b9d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9891567401effd4ee1565599f01fbd1e7d3abd4d6f6fec08d3254ace5bddb619", "generation_seconds_batch": 19.702283473103307, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.334439992904663, "target_z": 1.523437518305184, "ce": 6.205295085906982, "genuineness": 3.936227321624756, "identity": 0.6997448801994324, "hypothesis": "The 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_Pleasure_Ecstasy/55c4992c8a2c55d81f6302c44bda9930ba493e8788417348e295a65533426b9d.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "55ce6ca0a6b78ee59dcdf14c409a35879b53797303e61cb9ee443c8cb39c7d77", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "82911d907f06a078dc871f4680da3ad94e6c5fedcded041c963bc79e13e3ce9c", "generation_seconds_batch": 19.704209515010007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4584540128707886, "target_z": 1.7265625793224642, "ce": 6.141753673553467, "genuineness": 4.432034492492676, "identity": 0.5127031803131104, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/55ce6ca0a6b78ee59dcdf14c409a35879b53797303e61cb9ee443c8cb39c7d77.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": "560832f3382c1043c3cda793f1461b3d1917ee4335ce082079e84c2d91cce012", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1d63deed4ac28b5c2a5b21d7dd59b8bb1492e09c2ed4575d95d41cf1fb07a78e", "generation_seconds_batch": 16.005542194936424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11099433898925781, "target_z": -0.480468759152592, "ce": 6.054384231567383, "genuineness": 4.306513786315918, "identity": 0.29926806688308716, "hypothesis": "De weg gaat linksaf na de brug. Loop verder tot aan het kleine houthek. 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_Pleasure_Ecstasy/560832f3382c1043c3cda793f1461b3d1917ee4335ce082079e84c2d91cce012.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "562e961d331aae5e7fae56d847e5bfcc3aa2af73de4ab3829ef060dc191f957e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "22936fbf4ad63ef2fa9cf9251fab4439a126afcb2c44dae76b019a2e08017c47", "generation_seconds_batch": 15.515536317019723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5688921213150024, "target_z": 0.269531240847408, "ce": 6.141753673553467, "genuineness": 4.319066047668457, "identity": 0.6824648976325989, "hypothesis": "De deur 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_Pleasure_Ecstasy/562e961d331aae5e7fae56d847e5bfcc3aa2af73de4ab3829ef060dc191f957e.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "563f2286de38e9f32c749f6d633296e4f2da8408b96433ecfe563d47c1ee6811", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b6098237293a7479e173a4731be63074378cb672c41f541687b597249558e2bf", "generation_seconds_batch": 20.582040712004527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9767073392868042, "target_z": 0.9375, "ce": 6.24500846862793, "genuineness": 3.6851859092712402, "identity": 0.408855140209198, "hypothesis": "The door's still open. I put your coat on the chair. Tell me when you are ready.", "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_Pleasure_Ecstasy/563f2286de38e9f32c749f6d633296e4f2da8408b96433ecfe563d47c1ee6811.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "570b7adae33459af0de0cae155548c3d5091dcbbde075341afa29ac079f4d40e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "159815222f0b370d7cf813ad7539fe04dc4a39f9053998d006c03213064d5b7f", "generation_seconds_batch": 17.41127325000707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7971075773239136, "target_z": 2.281250073220736, "ce": 6.221180438995361, "genuineness": 4.381826400756836, "identity": 0.6228082180023193, "hypothesis": "La porte 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_Pleasure_Ecstasy/570b7adae33459af0de0cae155548c3d5091dcbbde075341afa29ac079f4d40e.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": "58330f25c56cee531402703a1502c29bfb3198d7525fca188af00247fe2d9236", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a5091ace8d77c98d932d4cf2b4799e56cd0234cfac97f0ec41fb6ca44fcfa80e", "generation_seconds_batch": 16.471577708958648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38913148641586304, "target_z": -0.024902323538025968, "ce": 6.41180419921875, "genuineness": 4.325342178344727, "identity": 0.43076467514038086, "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_Pleasure_Ecstasy/58330f25c56cee531402703a1502c29bfb3198d7525fca188af00247fe2d9236.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "5840059b7e8ce63f00faccd0c698ca8b20ef672f63698c85c22ee092261c1825", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f6365af31def9777addda1cb8ebdaaaa569ea4f2cdde07a8a38a3e4857526550", "generation_seconds_batch": 23.423947582952678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1913468837738037, "target_z": 1.2890624328809919, "ce": 6.252951145172119, "genuineness": 4.356721878051758, "identity": 0.41553837060928345, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5840059b7e8ce63f00faccd0c698ca8b20ef672f63698c85c22ee092261c1825.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "587b3eccc416120b322c62da8092f93df13ed77005384005afb253536759f07a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9677758634597cbb889d7f4a2bc696ae202a2af6f0e718fb6328adb7d6e0996a", "generation_seconds_batch": 15.615963623975404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6988683342933655, "target_z": 0.48242189788148004, "ce": 6.070269584655762, "genuineness": 4.507347106933594, "identity": 0.6137875318527222, "hypothesis": "La porte 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_Pleasure_Ecstasy/587b3eccc416120b322c62da8092f93df13ed77005384005afb253536759f07a.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "589e58b6fdb00cc49ffb5114f96cdec97306e338b85f86a2cf3c2b4cd6517148", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "965b889985d1c698fe36498480c62fb6e53801707c5f5a105c609933499cd630", "generation_seconds_batch": 17.35491967399139, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4006832540035248, "target_z": -0.005981450746851509, "ce": 6.070269584655762, "genuineness": 4.2249250411987305, "identity": 0.703506588935852, "hypothesis": "La porte 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_Pleasure_Ecstasy/589e58b6fdb00cc49ffb5114f96cdec97306e338b85f86a2cf3c2b4cd6517148.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "58d2bc0212c8ae210d577ff273410a926d4727ec9dbac1242accfeabadcb7a9e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6a107b65e13affb22e11f8af65a667c151369211b1bf85fbe8478b8098153d97", "generation_seconds_batch": 20.859317587921396, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1150306463241577, "target_z": 1.16406253050864, "ce": 6.038498878479004, "genuineness": 4.300237655639648, "identity": 0.29694485664367676, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/58d2bc0212c8ae210d577ff273410a926d4727ec9dbac1242accfeabadcb7a9e.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "58fa4307d592b19b6163471e27038c2e838ba3c37d294b907ef24eb20404b5d5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0a40b7ac24ed3cb3395daa1f81ad5ea5184aafc994e6f1da74e90110b9576f39", "generation_seconds_batch": 22.29504352598451, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9504736661911011, "target_z": 0.8945313384750562, "ce": 5.998785495758057, "genuineness": 4.218649387359619, "identity": 0.3337179720401764, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/58fa4307d592b19b6163471e27038c2e838ba3c37d294b907ef24eb20404b5d5.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "594f21ad8f42d838b395fb835fca07801a92f154c7bb2b7a2843be780091c6a8", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7c2dc50550b96e5ba458408025cebae8b5db6a35193743009877c362c96dec75", "generation_seconds_batch": 19.842164976056665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06568154692649841, "target_z": -0.554687493898272, "ce": 6.213237762451172, "genuineness": 4.143336772918701, "identity": 0.7353194952011108, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/594f21ad8f42d838b395fb835fca07801a92f154c7bb2b7a2843be780091c6a8.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": "5968a248cb566870c104d3d87e80e6bbf049a033ace1ed1b306c8881419f6bd5", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "63b6d581f8ee0404334749b8bd4055380896fdcb1396264724d19887b5949b30", "generation_seconds_batch": 17.679576912079938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5843938589096069, "target_z": 0.29492184906765595, "ce": 6.1894097328186035, "genuineness": 4.055472373962402, "identity": 0.5258612036705017, "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_Pleasure_Ecstasy/5968a248cb566870c104d3d87e80e6bbf049a033ace1ed1b306c8881419f6bd5.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "59963611a2710a3a70bf0a6c427451593896167ac842e56fcac93d1bec27d250", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cbdf14550c3efd9945fb2ea78b9923548d4b1d3e0af07f4aae52c9691b4d33b5", "generation_seconds_batch": 19.522450748016126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8734238147735596, "target_z": 2.406249975593088, "ce": 6.340320587158203, "genuineness": 4.319066047668457, "identity": 0.6875001788139343, "hypothesis": "La porte 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_Pleasure_Ecstasy/59963611a2710a3a70bf0a6c427451593896167ac842e56fcac93d1bec27d250.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "59ac721512d1c884bfb296dde3cf6beb07bdbc8d04cdde320d9ccd82fb65978e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "6b54d13b07667e56c7ba97809b0284e453df7dc1da73ac4893342f12048c01e5", "generation_seconds_batch": 20.04487241897732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6619026064872742, "target_z": 0.421874987796544, "ce": 6.221180438995361, "genuineness": 4.469690799713135, "identity": 0.06625691801309586, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/59ac721512d1c884bfb296dde3cf6beb07bdbc8d04cdde320d9ccd82fb65978e.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "59c47106110b17eafab0d0078f9726620c138c80ac0790677a81d26581e5a4bb", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "cab23bbc036999a5a91c29f4c7a2e12454ff9fbd2096c7afce5313610ce4e752", "generation_seconds_batch": 19.94707086600829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8543447256088257, "target_z": 2.374999951186176, "ce": 5.816103935241699, "genuineness": 3.7416701316833496, "identity": 0.3467564582824707, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/59c47106110b17eafab0d0078f9726620c138c80ac0790677a81d26581e5a4bb.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": "5a0b2e948525ff5b365ecac2b1e839875436514aee0349da525b1d82e2d63f67", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af85bff037548c82ecc5e79332b45e90db0419ea54e45cf35035ec0c8902104b", "generation_seconds_batch": 20.568467609002255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.000556230545044, "target_z": 0.9765625793224642, "ce": 6.284721851348877, "genuineness": 4.444586753845215, "identity": 0.7272998094558716, "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_Pleasure_Ecstasy/5a0b2e948525ff5b365ecac2b1e839875436514aee0349da525b1d82e2d63f67.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": "5af74fee8a0da91791b2d77d9be12cb348b9f11c47a13dfbf35043b6c46006ca", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b3de0e6fbb5411f4b178c403040ebed4e9dd4f307393f8b0504ce627f3e60fcd", "generation_seconds_batch": 15.973012748057954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17777110636234283, "target_z": -0.371093746949136, "ce": 6.213237762451172, "genuineness": 4.344170093536377, "identity": 0.4306979179382324, "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_Pleasure_Ecstasy/5af74fee8a0da91791b2d77d9be12cb348b9f11c47a13dfbf35043b6c46006ca.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "5b1af0d6b74bccdb227e337a3ada3f7565d15b12435828857f6066ed851d8aac", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "383efc23bc7bd6bb323c90ddcf3acb290216bed86be36334e41a55bb88dabadd", "generation_seconds_batch": 20.55365276010707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2724330425262451, "target_z": 1.4218750854241922, "ce": 5.8875885009765625, "genuineness": 4.193545341491699, "identity": 0.6051932573318481, "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_Pleasure_Ecstasy/5b1af0d6b74bccdb227e337a3ada3f7565d15b12435828857f6066ed851d8aac.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "5b4acf403f52032cf4f257adce3fc84ba4849dde30f17f045a032d1c8922c0ec", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "27af2a7c5b91fd5352c85153083342c432c2f39bc8e477ff5b0748c0ab7cac3c", "generation_seconds_batch": 21.73170935397502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6559404134750366, "target_z": 0.41210939177975203, "ce": 5.772419452667236, "genuineness": 4.15588903427124, "identity": 0.643287718296051, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5b4acf403f52032cf4f257adce3fc84ba4849dde30f17f045a032d1c8922c0ec.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "5b50221c4a3263d86a840ddaf5dfbd654b08c14c5e239dcba4d44e10ed20406b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d85d5641f467494f65e263d7d7800e226d6090ac9ecc4acdcd76b42c34e46ec", "generation_seconds_batch": 21.948647054028697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7684890031814575, "target_z": 2.2343751342380163, "ce": 6.443574905395508, "genuineness": 4.381826400756836, "identity": 0.6380192041397095, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5b50221c4a3263d86a840ddaf5dfbd654b08c14c5e239dcba4d44e10ed20406b.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "5b78480c369fe735d64ef561d658e9bb48cae0864acd41ba9cff29ac7dc36343", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6e94910d31a82edeafd54f0b04d6feebe3c5777a076d9ff07e9fd726587c0a34", "generation_seconds_batch": 23.17132010695059, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7334491014480591, "target_z": 0.5390624328809919, "ce": 6.181467056274414, "genuineness": 4.093128204345703, "identity": 0.055535364896059036, "hypothesis": "De deur 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_Pleasure_Ecstasy/5b78480c369fe735d64ef561d658e9bb48cae0864acd41ba9cff29ac7dc36343.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "5ba17adf1d85b2b16131ac91beb6c078c330a9dbc81976738cdf88f2173399dd", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "61d720be4e7870c123f0ae8557f8b10be4ddd219f9a414d7e597f5f9239d2c87", "generation_seconds_batch": 22.354467274970375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9027758836746216, "target_z": 0.8164061798301279, "ce": 6.252951145172119, "genuineness": 4.469690799713135, "identity": 0.4662618339061737, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5ba17adf1d85b2b16131ac91beb6c078c330a9dbc81976738cdf88f2173399dd.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "5bec48441f0af6473cbb715046a7bbf92a5838a916a7ffc5e43acc6242115db3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e358af81f84147fef1e61aefcf1b1dc5363ca3d9ff6047dc05f9430bc494bf80", "generation_seconds_batch": 22.705746703082696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8026107549667358, "target_z": 0.6523436981353119, "ce": 6.24500846862793, "genuineness": 4.595211505889893, "identity": 0.7310016751289368, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5bec48441f0af6473cbb715046a7bbf92a5838a916a7ffc5e43acc6242115db3.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "5bed131e2be9f4e02038f2049c8a89e36dbaf1326d7b2528f721ed429dde77ca", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "abafa553a6d4a6263e0f655e112d391f2b9167b76134aa29094330a60c457921", "generation_seconds_batch": 20.802036282024346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6058578491210938, "target_z": 0.33007815093234405, "ce": 6.23706579208374, "genuineness": 4.406930446624756, "identity": 0.5438451170921326, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5bed131e2be9f4e02038f2049c8a89e36dbaf1326d7b2528f721ed429dde77ca.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "5c1b5ae8d1ae8ea34c3431707e1c33601ee3f8532cf7827991fac4ca2c01a1dd", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "22456690a6f386d32d10e0cbadd02523e0c35022ad8a4024780e6820f392aac6", "generation_seconds_batch": 20.311819492955692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6714421510696411, "target_z": 0.4375, "ce": 6.149696350097656, "genuineness": 4.231201171875, "identity": 0.4340651333332062, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5c1b5ae8d1ae8ea34c3431707e1c33601ee3f8532cf7827991fac4ca2c01a1dd.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "5cb66899db828651e8eee887a95ff3e989cb3243f2436559c0088da99612a320", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1d66914bf76275279fe50ca466ee5a441a429a085842a8a7f68a267d67de0481", "generation_seconds_batch": 15.82911921502091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2485841512680054, "target_z": 1.382812506101728, "ce": 6.340320587158203, "genuineness": 4.545003414154053, "identity": 0.35452598333358765, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5cb66899db828651e8eee887a95ff3e989cb3243f2436559c0088da99612a320.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "5d0b2f78da2d6a05551e68338d6a967d63ea180ef4ad82c1abb5230818936b83", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6ac52c99929a6b95a6a26da04cf79a20a5f14d1b415eb8cba70b7c3722e12c7d", "generation_seconds_batch": 17.993122885003686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3321923613548279, "target_z": -0.118164063262716, "ce": 6.09409761428833, "genuineness": 3.7416701316833496, "identity": 0.3279660940170288, "hypothesis": "The 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_Pleasure_Ecstasy/5d0b2f78da2d6a05551e68338d6a967d63ea180ef4ad82c1abb5230818936b83.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "5d86c60f7c9869d7cb6214760a2d01a936cacf158f5e794c041068ef7c6e4e38", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c9b086ab1825feb9add1dea310658a1ec53555d6d5db3b614ffa0dc7274791be", "generation_seconds_batch": 20.13814310694579, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.313113272190094, "target_z": -0.14941408766962805, "ce": 6.38003396987915, "genuineness": 4.331617832183838, "identity": 0.4782889485359192, "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_Pleasure_Ecstasy/5d86c60f7c9869d7cb6214760a2d01a936cacf158f5e794c041068ef7c6e4e38.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "5d8967ed9504c328930d0a11dc0899ccc3e2fa4b4e8db1c0cf38e26f8b3f6f40", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9a4eba0fdcca7f964c8dbc459f3246eab90421560c86a82126a275e79d9c3bc7", "generation_seconds_batch": 20.670540262013674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6297066807746887, "target_z": 0.36914063262716, "ce": 6.133810997009277, "genuineness": 3.886019229888916, "identity": 0.3501376509666443, "hypothesis": "The 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_Pleasure_Ecstasy/5d8967ed9504c328930d0a11dc0899ccc3e2fa4b4e8db1c0cf38e26f8b3f6f40.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": "5dd648cf2104248a7cb7742d1fcdad3fe3e3331361acebe1f9d7e676d5ec7fa0", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d18108bb63db04038f49abf7f8aab7e467f8d8142f80224f1991843e70fa8df7", "generation_seconds_batch": 15.794977621058933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3342791199684143, "target_z": -0.11474611930098604, "ce": 5.959072113037109, "genuineness": 4.331617832183838, "identity": 0.5308793783187866, "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_Pleasure_Ecstasy/5dd648cf2104248a7cb7742d1fcdad3fe3e3331361acebe1f9d7e676d5ec7fa0.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "5df1f8237a008577f9c21cf83057c5680251408c090a09fd3ab6deabb8c03a1f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "794a3e4a6e23a9b0d9c2d7d7687e325b63ab664dec5bafc315af8659f78673f5", "generation_seconds_batch": 20.37799819302745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1436492204666138, "target_z": 1.21093746949136, "ce": 6.292664527893066, "genuineness": 4.432034492492676, "identity": 0.5968163013458252, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5df1f8237a008577f9c21cf83057c5680251408c090a09fd3ab6deabb8c03a1f.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "757bd0503a46a4f4d6741c8dc6419f61b35fee885902b3796b50b5105dac2eb7", "generation_seconds_batch": 15.248211741098203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0776059627532959, "target_z": -0.535156253050864, "ce": 6.0146708488464355, "genuineness": 4.406930446624756, "identity": 0.7811261415481567, "hypothesis": "La route tourna gauche après le pont, continue jusqu'à la petite barrière en bois. Je t'attendrai de l'autre côté.", "wer": 0.1, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.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": "5e14deb9d3e872f27d4cf598105173aa375557768cf5d72d4321a65dc250f8b2", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a735b17122cde49f64e7ec3c0bf1aec4ee714c7d6f26e0baa91c80fbdc6b0a84", "generation_seconds_batch": 21.6009789040545, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7382189035415649, "target_z": 0.546874987796544, "ce": 6.292664527893066, "genuineness": 4.482243061065674, "identity": 0.6821024417877197, "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_Pleasure_Ecstasy/5e14deb9d3e872f27d4cf598105173aa375557768cf5d72d4321a65dc250f8b2.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "5f01b974f8248c00c3c7665d59c8fd57f72a38ac3ab3526b6106e17e2cff782d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "812a978b1f0866c0a1a94022921d1731e0195b03ac519f8e456f2a89880ac973", "generation_seconds_batch": 19.330940724001266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7017122507095337, "target_z": 2.1250001464414723, "ce": 6.308549880981445, "genuineness": 4.287685871124268, "identity": 0.6632084846496582, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5f01b974f8248c00c3c7665d59c8fd57f72a38ac3ab3526b6106e17e2cff782d.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "5f091ce80259370dba996f0bdd015f24c67595afc8e8ee36ee883c7379f6432e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "98ce823441515e50d95b7063a39257e0555de4e1fdba60b2a0f6fc6192301be4", "generation_seconds_batch": 22.538327678921632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18731063604354858, "target_z": -0.355468759152592, "ce": 6.308549880981445, "genuineness": 4.507347106933594, "identity": 0.5052229166030884, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/5f091ce80259370dba996f0bdd015f24c67595afc8e8ee36ee883c7379f6432e.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "5f0934d50bff9239eb19ea869d86224a0e670d431ae18ae88bd081f283a3c6e1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "df80bf04f5838d1058d9e6ae72eb5369747149529fe62e1e7bfd3704b9561246", "generation_seconds_batch": 16.91437904292252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.043484091758728, "target_z": 1.046874987796544, "ce": 5.935244083404541, "genuineness": 3.553389072418213, "identity": 0.6583119630813599, "hypothesis": "The 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_Pleasure_Ecstasy/5f0934d50bff9239eb19ea869d86224a0e670d431ae18ae88bd081f283a3c6e1.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": "5f7833fe28a58da65a66ae791cb3698be991ca899383d68ba823b5ccccac5b9b", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2fd1061038afcd0ee245537e94ef5fea9ddde40b1c031925be402c8c29286e1f", "generation_seconds_batch": 15.98007430008147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9552433490753174, "target_z": 0.9023436981353119, "ce": 6.260893821716309, "genuineness": 4.494794845581055, "identity": 0.5121015310287476, "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_Pleasure_Ecstasy/5f7833fe28a58da65a66ae791cb3698be991ca899383d68ba823b5ccccac5b9b.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "5fd98ebfc44c8ac1f880674badfc1ff55bdd712d6a7c52a9ba91fc320664b424", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "59c9a2d9078b11cd7c66ff3eb2afdd428948024df569c96319d8d2d9dadadb2e", "generation_seconds_batch": 21.458389966050163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8066470623016357, "target_z": 2.296874987796544, "ce": 6.078212261199951, "genuineness": 3.9676074981689453, "identity": 0.5042332410812378, "hypothesis": "The 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_Pleasure_Ecstasy/5fd98ebfc44c8ac1f880674badfc1ff55bdd712d6a7c52a9ba91fc320664b424.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "5ffe32e3485425bfc51a7dd3c5cdb9cd7fae405e3cfd93f51498f818abf0189b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e11739d106a0889c70078d0ed698a95b82288e6fc36d53bc2c5930626b250423", "generation_seconds_batch": 20.739772993023507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9306610822677612, "target_z": 2.500000048813824, "ce": 6.038498878479004, "genuineness": 4.293961524963379, "identity": 0.5739717483520508, "hypothesis": "La porte 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_Pleasure_Ecstasy/5ffe32e3485425bfc51a7dd3c5cdb9cd7fae405e3cfd93f51498f818abf0189b.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "60417337c62f12c4f11197c2723905c088631d4be67e3058537ba72b3cfac996", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "94b84d0e7a9871a58226234b0438b237d5156a931b009a876e51a3fcc5de8e71", "generation_seconds_batch": 20.54654459701851, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2247352600097656, "target_z": 1.3437499267792639, "ce": 6.300607204437256, "genuineness": 4.093128204345703, "identity": 0.2220485508441925, "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_Pleasure_Ecstasy/60417337c62f12c4f11197c2723905c088631d4be67e3058537ba72b3cfac996.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "60463c1c42ad339ad6ddd74453e64ae0ca4fe4b24bb87c90d4d8cdd83578615b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "eaaa483fb170e5e60119e231e39fc25edb8669cba15c675d91789f5ff8a0bb48", "generation_seconds_batch": 23.676110872998834, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5104624629020691, "target_z": 0.173828126525432, "ce": 6.324435234069824, "genuineness": 4.400654315948486, "identity": 0.6476520895957947, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/60463c1c42ad339ad6ddd74453e64ae0ca4fe4b24bb87c90d4d8cdd83578615b.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "6077be425cd3cec60556854872b4479f1bb6133a6583c705c684a592481d5043", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "38a72e5502874ae96980f1d73d7a10d441e4ce851bbb528fbca39354784afc6e", "generation_seconds_batch": 20.83202970691491, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9306610822677612, "target_z": 2.500000048813824, "ce": 6.109982967376709, "genuineness": 4.331617832183838, "identity": 0.3765937089920044, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6077be425cd3cec60556854872b4479f1bb6133a6583c705c684a592481d5043.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "6078da3d2e2a1debdf60891e077c770b48cad4014e8afac45297cf46bef14cfc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b93061c1be88b6ea90bc742bbbd618cbd07735432df92b34e15fcd10105b52b7", "generation_seconds_batch": 19.331196562969126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6165897846221924, "target_z": 0.3476562042370399, "ce": 6.181467056274414, "genuineness": 4.15588903427124, "identity": 0.7662823796272278, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6078da3d2e2a1debdf60891e077c770b48cad4014e8afac45297cf46bef14cfc.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "6080285b096b6aa6fda782f94af145ea3b56320afb6c5feb79c7df1741ff8477", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2829b5a09062db0101149770645400f709ff90008f436b66453f4f95d2177f4a", "generation_seconds_batch": 20.57968131196685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8145352005958557, "target_z": 0.671874987796544, "ce": 6.53094482421875, "genuineness": 4.15588903427124, "identity": 0.3448435068130493, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6080285b096b6aa6fda782f94af145ea3b56320afb6c5feb79c7df1741ff8477.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "60ad5a475ad6995ebcf87b5efea5a2fd545a1ac33e6a654a966339b1224abf26", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f7903f09b9a52576d40df0d6077f85940493c3bf53bf213795837e022a82d13a", "generation_seconds_batch": 20.333195818937384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6046653985977173, "target_z": 0.328125012203456, "ce": 6.3641486167907715, "genuineness": 4.444586753845215, "identity": 0.4035916328430176, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/60ad5a475ad6995ebcf87b5efea5a2fd545a1ac33e6a654a966339b1224abf26.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "60ed99b7ac0e080ae997183939747e1ebcff830b6a667b53b569783e35e1b030", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5c6249f3549eeb0b9840152991a02716ecf5bc1b8a471051b2b7624fb7d6dacb", "generation_seconds_batch": 24.80495679494925, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35067522525787354, "target_z": -0.08789060822024797, "ce": 6.443574905395508, "genuineness": 4.13078498840332, "identity": 0.41986000537872314, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/60ed99b7ac0e080ae997183939747e1ebcff830b6a667b53b569783e35e1b030.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "6142d1041b5b27596a80dd892404989f32057bcac7f170a27497c970bfec112f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "346fe35d146cc8eb166a2de9176a9293e76445667c9bd8f47617709fb93051ee", "generation_seconds_batch": 14.61827883508522, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2533539533615112, "target_z": 1.3906250610172801, "ce": 6.260893821716309, "genuineness": 3.911123275756836, "identity": 0.31325316429138184, "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_Pleasure_Ecstasy/6142d1041b5b27596a80dd892404989f32057bcac7f170a27497c970bfec112f.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "61482b9fa5cca172d349fb9ee13055fd4546fa522e24d53c6af8a93cc17cba39", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "62b12b473092e869279345df472d4001b18dc3cf92649e86fbdcfed4f648086c", "generation_seconds_batch": 20.293403872055933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1198004484176636, "target_z": 1.1718750854241922, "ce": 6.292664527893066, "genuineness": 4.231201171875, "identity": 0.6654059290885925, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/61482b9fa5cca172d349fb9ee13055fd4546fa522e24d53c6af8a93cc17cba39.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": "61b47623e7db3b38f1113b02bbfbe9e2d59bb04c9f66ed617c288b9d8e2a7a63", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e29848da94159ee75cfe1d8224735ced97f8bdaa53f4bbc3db0a6d2963e0fbc7", "generation_seconds_batch": 15.496268370072357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6881363391876221, "target_z": 0.464843746949136, "ce": 6.268836498260498, "genuineness": 4.545003414154053, "identity": 0.4428880214691162, "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_Pleasure_Ecstasy/61b47623e7db3b38f1113b02bbfbe9e2d59bb04c9f66ed617c288b9d8e2a7a63.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "6203d5250c8bacb833cc33f3f290083f1edec675e4cb54287b6437d1bd80dc46", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "9067b64566ed5d51265590743f83ca0816c67f99a10bdf40291f20c8bfc662af", "generation_seconds_batch": 23.463221274898387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5252307653427124, "target_z": 1.8359375671190081, "ce": 5.967014789581299, "genuineness": 4.005263805389404, "identity": 0.45311352610588074, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6203d5250c8bacb833cc33f3f290083f1edec675e4cb54287b6437d1bd80dc46.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "6347fdc5a474b117968d60a448ab526c3278b6a72f6967484f534b706fe2c4a2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ac926d008bf5bb83ea1775ee3f78025a63e9d4f2fda5f6958e4dac6b3dbef71a", "generation_seconds_batch": 20.24148485902697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.968819260597229, "target_z": 2.562500097627648, "ce": 6.221180438995361, "genuineness": 4.055472373962402, "identity": 0.6437598466873169, "hypothesis": "La porte 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_Pleasure_Ecstasy/6347fdc5a474b117968d60a448ab526c3278b6a72f6967484f534b706fe2c4a2.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "634cae3a66f8bd5ca24fc285d41b87371e74286b5020f16a6db948f7eb0a31da", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "41155567d13939cca8e1ba5b887a2073be3048a6f8e7016a4e0e0e42d2d7e216", "generation_seconds_batch": 21.275077964994125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9552433490753174, "target_z": 0.9023436981353119, "ce": 6.316492557525635, "genuineness": 4.005263805389404, "identity": 0.27573952078819275, "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_Pleasure_Ecstasy/634cae3a66f8bd5ca24fc285d41b87371e74286b5020f16a6db948f7eb0a31da.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "63777aaac4775135c9c522ff5c0d6c4c443eb0d2cd7aba4258caf1105de792f0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ed8bf7edeededcea417248138575084fc300c5ae0c5a7d889eaf50e7144c221a", "generation_seconds_batch": 17.62727914901916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.692172646522522, "target_z": 2.109375036610368, "ce": 6.173524379730225, "genuineness": 4.65797233581543, "identity": 0.506005048751831, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/63777aaac4775135c9c522ff5c0d6c4c443eb0d2cd7aba4258caf1105de792f0.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "63869e874ff0450936dc9c1aa55ab7344100c325686c7fa1b737e5293a121c1c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f076b60b000f02a03d1cc1aa504a6897ced4d22cd9fb41ce431926c14c76e159", "generation_seconds_batch": 19.603843186981976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6253958940505981, "target_z": 2.000000048813824, "ce": 5.990842819213867, "genuineness": 3.8295347690582275, "identity": 0.4372590184211731, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/63869e874ff0450936dc9c1aa55ab7344100c325686c7fa1b737e5293a121c1c.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "639b20c203b06db14b9bd251438e2603672fe78d47b51651b8a3d086669c36be", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "b39f384e6ae64e55d0597800330206d664671ddeeb394f733d93865e9c83a963", "generation_seconds_batch": 17.92179599800147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2505100965499878, "target_z": -0.25195308991506393, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.4499812722206116, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/639b20c203b06db14b9bd251438e2603672fe78d47b51651b8a3d086669c36be.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "64863747b8cb484185ef38a89f2feb36a185cd5a35b86cccf0e9ff28d047ea5b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e3cac36d2e73b68e75a7ad770a1385827dfb9af17d46ed829b4593d1e3b3c088", "generation_seconds_batch": 24.15872675809078, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6349353790283203, "target_z": 2.015624963389632, "ce": 5.974957466125488, "genuineness": 3.9173994064331055, "identity": 0.2996083199977875, "hypothesis": "He encontrado en la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/64863747b8cb484185ef38a89f2feb36a185cd5a35b86cccf0e9ff28d047ea5b.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": "656e484dc8a71b2d4e50fd2bb739f9bbb2620daa3329d0d97c912840b84e599d", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "db2ea06ce09c2967caf81d84ab48c40a8650affbb54d5db806bb61a6f9a02937", "generation_seconds_batch": 15.794977621058933, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7096003293991089, "target_z": 0.5000000488138241, "ce": 6.3641486167907715, "genuineness": 4.65797233581543, "identity": 0.4117862582206726, "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_Pleasure_Ecstasy/656e484dc8a71b2d4e50fd2bb739f9bbb2620daa3329d0d97c912840b84e599d.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "657bee906df0324e4831c724769c0dada516b0d845262efc7e20c2f1e9cd3a37", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "31c19a2cdec1aa3ce327165a30c7358f5b395c0de4aab9e13cf5dbf7e7b755f5", "generation_seconds_batch": 14.64427795400843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9402005672454834, "target_z": 2.515624963389632, "ce": 6.109982967376709, "genuineness": 4.344170093536377, "identity": 0.4639996886253357, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/657bee906df0324e4831c724769c0dada516b0d845262efc7e20c2f1e9cd3a37.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "65aeff8fb24f0f15def348f80b54276b52413990e0c93e3013ff72cd18699525", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 127, "seconds_generated": 10.16, "mp3_sha256": "46064114e06f7eecc8c9128130067c53fa10dfc440c6c968198d9fb445141830", "generation_seconds_batch": 19.65980603499338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4250656366348267, "target_z": 1.6718750854241922, "ce": 6.467403411865234, "genuineness": 4.005263805389404, "identity": 0.42561572790145874, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschaffen.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/65aeff8fb24f0f15def348f80b54276b52413990e0c93e3013ff72cd18699525.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": "65b75b769b1dd946bfeb64eea28161410ce13dafdf4b93ae30fc8e5ed1831aaf", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1e4c3b6f3cd6bc7eaa88ba2f31b4878d2d2bc5538a6610735971018468db933", "generation_seconds_batch": 22.036086176987737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3503771126270294, "target_z": -0.08837889290246997, "ce": 6.499174118041992, "genuineness": 4.444586753845215, "identity": 0.310584157705307, "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_Pleasure_Ecstasy/65b75b769b1dd946bfeb64eea28161410ce13dafdf4b93ae30fc8e5ed1831aaf.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "65cff12207b8d0f1f8af27cbd952adfadea0bed661b029bc398375d9ddafb50b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "49f08f2d496b84d3c9c4b4f3bea46e85457f35468a8275e839e08733766ee38e", "generation_seconds_batch": 16.003340975032188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8884665966033936, "target_z": 0.7929687103387679, "ce": 6.395919322967529, "genuineness": 4.13078498840332, "identity": 0.30407193303108215, "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_Pleasure_Ecstasy/65cff12207b8d0f1f8af27cbd952adfadea0bed661b029bc398375d9ddafb50b.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": "65d89f3cbf6fda8d5b2142d208a55138775bd377216de7a4b223bd7da4303971", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "872277364bec2dfd86b658e4a8d5f72ad95aba66609f8a9cf3070b2b86a46bcf", "generation_seconds_batch": 14.796279111993499, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.466938316822052, "target_z": 0.10253905105925998, "ce": 6.372091293334961, "genuineness": 4.231201171875, "identity": 0.6531111001968384, "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_Pleasure_Ecstasy/65d89f3cbf6fda8d5b2142d208a55138775bd377216de7a4b223bd7da4303971.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "65fe564e52a78f8e1da1d6f3f1fd8a96df2c88996075fd4cf5cfd8b2b3017713", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c07c9e9ba4e97d695f87edac42f53f88357295bd9912ea0f7d0785490dca3e2d", "generation_seconds_batch": 17.560218233964406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1436492204666138, "target_z": 1.21093746949136, "ce": 6.356205940246582, "genuineness": 4.250029563903809, "identity": 0.26080793142318726, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/65fe564e52a78f8e1da1d6f3f1fd8a96df2c88996075fd4cf5cfd8b2b3017713.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "664d59ea8d173a59efe6215b883bf98f2c302d73caafcbb671ae9d1b0c2ac23a", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f8fa11d4f7d7c04baaee2ffbee0934eb23d4c0be7e17b34e3c45de3fdb05d44c", "generation_seconds_batch": 16.717534753028303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23739321529865265, "target_z": -0.273437493898272, "ce": 6.395919322967529, "genuineness": 4.218649387359619, "identity": 0.42782580852508545, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/664d59ea8d173a59efe6215b883bf98f2c302d73caafcbb671ae9d1b0c2ac23a.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "6664459c07254099f5ae0df336662a6a6225ba6a053c415a85fc8fd7cc84c42d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "703f6e0d549ccc6d3cbe474a16ae979ac90803e65380b23fe35bfd90b09db6ef", "generation_seconds_batch": 21.820775259984657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5109214782714844, "target_z": 1.8125000976276482, "ce": 6.284721851348877, "genuineness": 4.030367851257324, "identity": 0.15039725601673126, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6664459c07254099f5ae0df336662a6a6225ba6a053c415a85fc8fd7cc84c42d.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "67058d5690952f066dc03eb61e25b496125b0cd04d49cd816e121ded0c5df824", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c1006335ad717d865e4df01dfd28382839add508ff18071f339db443132693b4", "generation_seconds_batch": 20.78287438803818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1786890029907227, "target_z": 2.906249975593088, "ce": 6.157639026641846, "genuineness": 4.21237325668335, "identity": 0.7020227909088135, "hypothesis": "La porte 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_Pleasure_Ecstasy/67058d5690952f066dc03eb61e25b496125b0cd04d49cd816e121ded0c5df824.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": "67c85f67722984f87d31d3b86d85e5c6a30d6cf623bdc4d582a4e1f01f9d84ae", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b9f9b7525015f49a2b4d0da88b487e9fc92d0aefafc94797fc24da21d11c2c1e", "generation_seconds_batch": 17.48583423101809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5593525767326355, "target_z": 0.25390622864395196, "ce": 6.205295085906982, "genuineness": 4.394378662109375, "identity": 0.6467573046684265, "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_Pleasure_Ecstasy/67c85f67722984f87d31d3b86d85e5c6a30d6cf623bdc4d582a4e1f01f9d84ae.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": "686a603159d2f3fb3791207acccf47124b9b0697493c5ae3088dcf7c46a016a8", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e0f5f47af19284c8dc29a2e62d6456e6dbd2ef6635b5823033074f8da647727", "generation_seconds_batch": 15.304053961997852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5307339429855347, "target_z": 0.20703119203358392, "ce": 6.356205940246582, "genuineness": 4.432034492492676, "identity": 0.49572813510894775, "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_Pleasure_Ecstasy/686a603159d2f3fb3791207acccf47124b9b0697493c5ae3088dcf7c46a016a8.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "698d181307a109d2a2386d3c73915db5870e214816e894b9d4b1c688da843dd8", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "086c84ad22d21d439bd125674eadc8b4d5aab94ee2bec5950d3f198112ab2bbc", "generation_seconds_batch": 19.842164976056665, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1264961063861847, "target_z": -0.45507810211851996, "ce": 6.213237762451172, "genuineness": 4.362998008728027, "identity": 0.7354256510734558, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/698d181307a109d2a2386d3c73915db5870e214816e894b9d4b1c688da843dd8.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "69f5ee2cea3632f572d413759d6b588345b249271c7429f167049f7852336d22", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8a6c991776cf359723576c96ee6d891fe22aaae804b95899e30fe23a01948f64", "generation_seconds_batch": 19.338234868948348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7017122507095337, "target_z": 2.1250001464414723, "ce": 6.213237762451172, "genuineness": 4.394378662109375, "identity": 0.7025516033172607, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/69f5ee2cea3632f572d413759d6b588345b249271c7429f167049f7852336d22.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "6a44ec4e1df3e7ebb5d34a5bc01ea9d9193c57a3d2f83bfb4f0e11c46ea018d4", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "057b250a529e1d005b68dc022e6cc7b73fb3c9af238c3608f3bbc98188babb03", "generation_seconds_batch": 15.023210840066895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.720791220664978, "target_z": 2.156249975593088, "ce": 5.911416053771973, "genuineness": 4.093128204345703, "identity": 0.5195647478103638, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6a44ec4e1df3e7ebb5d34a5bc01ea9d9193c57a3d2f83bfb4f0e11c46ea018d4.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "be5a82668de9583bd539ea4e335d100c331abdbf030dd6b6cb833c8aa7119124", "generation_seconds_batch": 15.38880374492146, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046602457761764526, "target_z": -0.585937518305184, "ce": 6.403861999511719, "genuineness": 3.9801597595214844, "identity": 0.29537057876586914, "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_Pleasure_Ecstasy/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "6ad6ff18e48df1fdfd3134c6382efcc6ce47aab9561e416f4bedc3dce1dc8436", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9a6e19d8967fe8eb41f4dd9da7b442db9a49c83a050a0dfc23bd798082060fd0", "generation_seconds_batch": 21.322301398962736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.000556230545044, "target_z": 0.9765625793224642, "ce": 6.300607204437256, "genuineness": 4.519899368286133, "identity": 0.5389436483383179, "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_Pleasure_Ecstasy/6ad6ff18e48df1fdfd3134c6382efcc6ce47aab9561e416f4bedc3dce1dc8436.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "6b1b4f69a2ba1dcefa46ebacb300c5121d6f58064be1c01ddb88f1d6c0c1e7a3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9a527acd5a67d58e5d51c05b5ed5ca6b094d76c0033882cd577d7abb8e1018e1", "generation_seconds_batch": 19.31928555702325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.043484091758728, "target_z": 1.046874987796544, "ce": 6.141753673553467, "genuineness": 4.482243061065674, "identity": 0.8044978976249695, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6b1b4f69a2ba1dcefa46ebacb300c5121d6f58064be1c01ddb88f1d6c0c1e7a3.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "6b23f962e26f8dbf7da58f22de1156de9882682bdf1c78cda5785ee76da287dd", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ff6b29a697a0f3ca5de5a8e88a50470f44bd396e691587097ba7cecf2e669a62", "generation_seconds_batch": 19.81610798393376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9306610822677612, "target_z": 2.500000048813824, "ce": 5.919358730316162, "genuineness": 4.532451152801514, "identity": 0.4344978332519531, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6b23f962e26f8dbf7da58f22de1156de9882682bdf1c78cda5785ee76da287dd.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "34e38db6fc513b4b9a80064774d7a227893b834f52b998d4ef63afea5cc5e976", "generation_seconds_batch": 15.463117914041504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09430015087127686, "target_z": -0.507812506101728, "ce": 6.197352409362793, "genuineness": 4.65797233581543, "identity": 0.7134343385696411, "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_Pleasure_Ecstasy/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "6c1e533886a4fe1cb8cf8aadc98c6b7f113d4b39d76439ddfc76149bec867a61", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "916f0e52ba6af25dc0c494ef29125265d2e07fbab77366b6cd9fd0e4cf2bf95d", "generation_seconds_batch": 22.15283786796499, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8216898441314697, "target_z": 0.683593722542224, "ce": 6.09409761428833, "genuineness": 4.68307638168335, "identity": 0.5526318550109863, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6c1e533886a4fe1cb8cf8aadc98c6b7f113d4b39d76439ddfc76149bec867a61.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "6c51424bc0886ca3cf517d73aab6cb91ad02b2a43bd41572ffa1e9ea4664dcb3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "17b0a5ce9900b838681008c800c59e4c335d1503379853c9a6f72333e038143e", "generation_seconds_batch": 21.24071636691224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28449466824531555, "target_z": -0.19628907546617202, "ce": 6.197352409362793, "genuineness": 4.055472373962402, "identity": 0.3901611566543579, "hypothesis": "The 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_Pleasure_Ecstasy/6c51424bc0886ca3cf517d73aab6cb91ad02b2a43bd41572ffa1e9ea4664dcb3.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "6c6c3c4d6c7ee2adde6073b561decf1c8d47637999ca01d6292e62fbc032e177", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f2e7221e92a0d9a8a828385d58802dbf66a569f50b0753284fbc4bcbefc613db", "generation_seconds_batch": 19.22687830403447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4913833737373352, "target_z": 0.14257810211851996, "ce": 6.0146708488464355, "genuineness": 3.7542223930358887, "identity": 0.47801774740219116, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6c6c3c4d6c7ee2adde6073b561decf1c8d47637999ca01d6292e62fbc032e177.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "6c998810993b27b7a40062179642312a3b94e17b7e72769844de9ede1a072efc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b689d0d421d2cd9f166d69e93e2a2d4066c8ebd9a91806bf3bec78ad82805b2d", "generation_seconds_batch": 15.200551163987257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4059865474700928, "target_z": 1.6406250610172801, "ce": 6.308549880981445, "genuineness": 3.7667744159698486, "identity": 0.4682937264442444, "hypothesis": "The 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_Pleasure_Ecstasy/6c998810993b27b7a40062179642312a3b94e17b7e72769844de9ede1a072efc.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": "6d3a28b2223104bef622d0b440eafecd0299c8f48d6750da8290ba183fbc037a", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1f6e137789c476298c4fb6d8e7b769f2a1380d54679adb71c211d716bd039694", "generation_seconds_batch": 17.251630749902688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5593525767326355, "target_z": 0.25390622864395196, "ce": 6.427689552307129, "genuineness": 4.325342178344727, "identity": 0.3590853810310364, "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_Pleasure_Ecstasy/6d3a28b2223104bef622d0b440eafecd0299c8f48d6750da8290ba183fbc037a.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "6d3b56a14829b55a37deee0e8de159cc2ef2feffc825f720273ef442ca1aa683", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d9a4be7be412d087043e39255fc8cd5fb034f151392bdcfa3446541e8a663339", "generation_seconds_batch": 21.402558127068914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0355958938598633, "target_z": 2.671874890168896, "ce": 6.062326908111572, "genuineness": 4.256305694580078, "identity": 0.4878295063972473, "hypothesis": "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_Pleasure_Ecstasy/6d3b56a14829b55a37deee0e8de159cc2ef2feffc825f720273ef442ca1aa683.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "6dad51f02e7744287070d2e8f6d176cb601e3642165318d6d11c69f46dc190fc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4ed296e3850c2a620b05dac60b7b4865f962ea4bfc49dddacddbe0635ebb5768", "generation_seconds_batch": 21.661287892027758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4489144086837769, "target_z": 1.71093746949136, "ce": 6.221180438995361, "genuineness": 3.911123275756836, "identity": 0.3465989828109741, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6dad51f02e7744287070d2e8f6d176cb601e3642165318d6d11c69f46dc190fc.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "6eae6a923d900a8172e6d95befbb465206faf2b7b2716c17766de1151b709f36", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dfa51b0cefaf03c0822b66a02c589850fae87df323c6891d5f75bf3e9bac1c5c", "generation_seconds_batch": 22.67602136696223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5241755247116089, "target_z": 0.19628902665234796, "ce": 6.260893821716309, "genuineness": 4.457139015197754, "identity": 0.5964891910552979, "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_Pleasure_Ecstasy/6eae6a923d900a8172e6d95befbb465206faf2b7b2716c17766de1151b709f36.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "6ebdf7c3cbca13f02606e32355936f619d0243d51694c537c082714e4733045d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3506bc2772deadc516e6b3cf77a49ee16bf634b097a3a64eb63eaf2944627803", "generation_seconds_batch": 17.094967384939082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.334439992904663, "target_z": 1.523437518305184, "ce": 5.967014789581299, "genuineness": 4.319066047668457, "identity": 0.2313641905784607, "hypothesis": "De deur 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_Pleasure_Ecstasy/6ebdf7c3cbca13f02606e32355936f619d0243d51694c537c082714e4733045d.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "6f3841a68b65922475973ff8501ea7d98e5bb1cdfbad362cce014ea73a4b99cf", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cea197608a1aacb5991a75ac7765a46990f4f2236cab1b2dff9e111d478459da", "generation_seconds_batch": 19.338234868948348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2915120124816895, "target_z": 1.4531249145758078, "ce": 6.078212261199951, "genuineness": 4.331617832183838, "identity": 0.5649502277374268, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6f3841a68b65922475973ff8501ea7d98e5bb1cdfbad362cce014ea73a4b99cf.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": "6f6d666ab4df081da662d4afcd088e8a70e4c84b9cca9b7ab26f56ef77999dcd", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fcc443ddb2d113bdb145231ea265052b7478a6edb498a432e21d8ce0efce8e4f", "generation_seconds_batch": 16.00560619099997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8598480224609375, "target_z": 0.746093771356048, "ce": 6.3641486167907715, "genuineness": 4.482243061065674, "identity": 0.6730472445487976, "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_Pleasure_Ecstasy/6f6d666ab4df081da662d4afcd088e8a70e4c84b9cca9b7ab26f56ef77999dcd.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "6f84bb7ff38f2f689eb412af802676c3aee883db1fdacd15d5e3bf1fadced48c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a6596a434fc11b6eed5adf04a2bf291cfc62140da85e8433642373dbbc4637d9", "generation_seconds_batch": 19.547768446966074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.320130705833435, "target_z": 1.500000048813824, "ce": 6.324435234069824, "genuineness": 4.042920112609863, "identity": 0.36339303851127625, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6f84bb7ff38f2f689eb412af802676c3aee883db1fdacd15d5e3bf1fadced48c.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "6f9fc1c03147663c25064f5bab4a2e398d4ed2e68164b5b82788f90f64aca6c1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "162e134650f0c528a40345d5eebbba0d479b72ca056266a85dcb3671d9b92f91", "generation_seconds_batch": 20.677822713973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8829634189605713, "target_z": 2.421875085424192, "ce": 5.847874641418457, "genuineness": 4.381826400756836, "identity": 0.5636717081069946, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6f9fc1c03147663c25064f5bab4a2e398d4ed2e68164b5b82788f90f64aca6c1.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "6fb5a28d28c8247200688770616db12580adf83202e488761439dc12852b53b4", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "16bf4b1f73e33c879c3e6780290ce954f24d2cc251a087bf905db7940fdd4269", "generation_seconds_batch": 20.50080117501784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.334439992904663, "target_z": 1.523437518305184, "ce": 6.348263263702393, "genuineness": 4.143336772918701, "identity": 0.3494546711444855, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/6fb5a28d28c8247200688770616db12580adf83202e488761439dc12852b53b4.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": "7002a0d993dd62aad9ed850be9ea914e7d40a502431578ae7a529c3b425f0a52", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18b4ea8edc0b9474b50f126d481325e4dc09e8dc38d42a6a4f70ddcffb7c9b6e", "generation_seconds_batch": 19.558017925941385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2962818145751953, "target_z": 1.46093746949136, "ce": 6.1894097328186035, "genuineness": 4.419482707977295, "identity": 0.6798180937767029, "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_Pleasure_Ecstasy/7002a0d993dd62aad9ed850be9ea914e7d40a502431578ae7a529c3b425f0a52.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "707cd0baadcb35dcda24b80b6e2e19082357c73cc8e33af86fa7daaa4765d46c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "848d2b3729733ba3650bb66ef3986fdb846e9725e971933f2a23612ee7382d34", "generation_seconds_batch": 21.149578440003097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.350400686264038, "target_z": 3.1875, "ce": 6.054384231567383, "genuineness": 4.017816066741943, "identity": 0.42337125539779663, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/707cd0baadcb35dcda24b80b6e2e19082357c73cc8e33af86fa7daaa4765d46c.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": "70d746931afd25da78fdcb0bc97a9451125f47c559ca03bfd4bcbf450825e3e8", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2398ba052d397067da8913457a8414b01adaa4cc860ed13fa40f2d63ff7db180", "generation_seconds_batch": 22.036086176987737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23023855686187744, "target_z": -0.285156253050864, "ce": 6.38003396987915, "genuineness": 4.162164688110352, "identity": 0.5278621315956116, "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_Pleasure_Ecstasy/70d746931afd25da78fdcb0bc97a9451125f47c559ca03bfd4bcbf450825e3e8.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "7101b896c5db3346116b1da98fd6711d044aa59ea7bd9413d7cdb21b53911737", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1ecb4c396e52bcf736704b94ebb102f246e97eb0fb58fcdd857cad93ec772e64", "generation_seconds_batch": 22.56392724404577, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5557752847671509, "target_z": 0.24804691008493607, "ce": 6.086154937744141, "genuineness": 4.243753433227539, "identity": 0.06574854254722595, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7101b896c5db3346116b1da98fd6711d044aa59ea7bd9413d7cdb21b53911737.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "713b7a484aadb65c15960e84e0bc2a541be3552b5f7e13ac53233c36bbd796a7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "af1bd2e9856b57de97ad020067a08eb64111fc864417fd516dc76db152a4c726", "generation_seconds_batch": 19.85450871498324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5182133316993713, "target_z": 0.186523430635556, "ce": 6.197352409362793, "genuineness": 4.632867813110352, "identity": 0.8308703899383545, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/713b7a484aadb65c15960e84e0bc2a541be3552b5f7e13ac53233c36bbd796a7.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "7176539df0c764b2eae03e37559ee306fdda7ed32cf11daf51b1272bd880126e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f6d3a2d72186a4455aadf5c699859dda383b81c20706dfaf11b5638367088eee", "generation_seconds_batch": 20.13457695604302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5013818740844727, "target_z": 1.796874987796544, "ce": 6.38003396987915, "genuineness": 4.770940780639648, "identity": 0.630719006061554, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7176539df0c764b2eae03e37559ee306fdda7ed32cf11daf51b1272bd880126e.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "719e7a5f3cfc06dbf23a0000aa81c49467c5fd48093ae9f408ca842911d84d5b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fa557e434e684dfd0ec0528dff72e838989e503582e70b03e3603d9ea12318f3", "generation_seconds_batch": 23.705036693951115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1865772008895874, "target_z": 1.2812500732207361, "ce": 5.645336627960205, "genuineness": 3.6914620399475098, "identity": 0.37953874468803406, "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_Pleasure_Ecstasy/719e7a5f3cfc06dbf23a0000aa81c49467c5fd48093ae9f408ca842911d84d5b.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": "71a8911dc65ce673962210ded760593dcb844f9e5eaf8b267c42980bb099b46e", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b7ed501046a5092580ee48f5d7b161584325a9f68c5107441fee300cc07bbf9", "generation_seconds_batch": 17.87501128797885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30178508162498474, "target_z": -0.16796875915259202, "ce": 6.221180438995361, "genuineness": 4.306513786315918, "identity": 0.5496479868888855, "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_Pleasure_Ecstasy/71a8911dc65ce673962210ded760593dcb844f9e5eaf8b267c42980bb099b46e.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "71ddd442d977893274a858f4659a8d0a9bda803c6584edecfcb740f0b404ce18", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5048c58620dc20d6edff675ecf96719ceb38fefb7a2921aeefed79fcd35afb1a", "generation_seconds_batch": 20.49081054504495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.140530824661255, "target_z": 2.843749926779264, "ce": 6.070269584655762, "genuineness": 4.193545341491699, "identity": 0.5208777189254761, "hypothesis": "La porte 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_Pleasure_Ecstasy/71ddd442d977893274a858f4659a8d0a9bda803c6584edecfcb740f0b404ce18.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "724a82739480c2d2f2773782b1e370780d11942e009354ceb85022da8d640952", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "57f78b8869f6b51d90e185cf4e05c7747dbb20b8ae0646e251393bc36adc3135", "generation_seconds_batch": 19.64325412805192, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38987675309181213, "target_z": -0.02368163623938299, "ce": 6.157639026641846, "genuineness": 4.306513786315918, "identity": 0.5767936706542969, "hypothesis": "La porte 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_Pleasure_Ecstasy/724a82739480c2d2f2773782b1e370780d11942e009354ceb85022da8d640952.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "736dacde39318ac42a5baed9fdbd30efeb53189e0aae41223dba9199be8e85cc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cddb053ae69988ea5881966168759475cce787808d1e876f30530f04888d4015", "generation_seconds_batch": 21.562419555033557, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.40763783454895, "target_z": 3.2812498779654398, "ce": 5.403085231781006, "genuineness": 3.8922953605651855, "identity": 0.40188682079315186, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/736dacde39318ac42a5baed9fdbd30efeb53189e0aae41223dba9199be8e85cc.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "73c79cdf0cf8628e5fe6f20dd73a1051c9b5b248e1f0cc3c628f702bb9371792", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1c19b8471654de4957eb4b117026a5f5800fdd0f8969d1e2afe9278560477a49", "generation_seconds_batch": 19.372665864997543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.102372646331787, "target_z": 2.7812498779654398, "ce": 5.752562999725342, "genuineness": 3.7918784618377686, "identity": 0.5689067840576172, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/73c79cdf0cf8628e5fe6f20dd73a1051c9b5b248e1f0cc3c628f702bb9371792.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "74118e1f15f0f99c0f4e5249ac52e2fac5b1ca11ba31520e92f127094ce49355", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "85cf042ab1bb04d3d888d4e3562ac3098f80fa7a17ac9203a21700776d629483", "generation_seconds_batch": 15.455411802046001, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38257303833961487, "target_z": -0.03564453773308601, "ce": 6.332377910614014, "genuineness": 4.344170093536377, "identity": 0.7016837000846863, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/74118e1f15f0f99c0f4e5249ac52e2fac5b1ca11ba31520e92f127094ce49355.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "74516d68c6aabb895ea309c09fb76de8dcec08e9c2901c498f27b43f02110050", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c7b41f84161ed011f80e3064b6daca4ab2a295d3bddadb570a5e67520fab1e53", "generation_seconds_batch": 14.796340096043423, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4489144086837769, "target_z": 1.71093746949136, "ce": 6.229123115539551, "genuineness": 4.444586753845215, "identity": 0.7641959190368652, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/74516d68c6aabb895ea309c09fb76de8dcec08e9c2901c498f27b43f02110050.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": "74eb51573b73f4f456be1aa8145143166f0dcaae654afb378977442731c847d6", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c5a150a456c8390465b969f74a190d4811a5c10779159406ccf9e8d21035b41e", "generation_seconds_batch": 20.579113692045212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2683967053890228, "target_z": -0.222656253050864, "ce": 6.213237762451172, "genuineness": 4.3504462242126465, "identity": 0.30729609727859497, "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_Pleasure_Ecstasy/74eb51573b73f4f456be1aa8145143166f0dcaae654afb378977442731c847d6.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "757e83beb9dbcab41e26d752aca0b8ca281f439faad4b283bf08b43b35fe1789", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "75aab2854b95e3ebb72bac66e84d11f6af4f3b7c484591600b4bc604950cf656", "generation_seconds_batch": 19.688823832082562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.07687246799469, "target_z": 1.101562481694816, "ce": 6.38797664642334, "genuineness": 4.457139015197754, "identity": 0.6210639476776123, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/757e83beb9dbcab41e26d752aca0b8ca281f439faad4b283bf08b43b35fe1789.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "759ebe5a7d909f5871c471cbc201ed59c824efd8c65c21cf3b4ba679f6d7e4cf", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "76870bab117eee2e4b6d7b23de4f468e79c5b9c2e1209d5b072b145310ee02e8", "generation_seconds_batch": 19.672999900998548, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9290096759796143, "target_z": 0.8593750366103681, "ce": 6.157639026641846, "genuineness": 3.798154592514038, "identity": 0.26200374960899353, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/759ebe5a7d909f5871c471cbc201ed59c824efd8c65c21cf3b4ba679f6d7e4cf.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "766b290af56b309649e253aa6195eb230f3d6e9e6e42e57499c981fad859afbb", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0f2c746a8a2e134ee8f61fe05b3d5b52ea16224d2fa250757896c0955e838c0f", "generation_seconds_batch": 23.684504356002435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48542118072509766, "target_z": 0.132812506101728, "ce": 6.062326908111572, "genuineness": 4.13078498840332, "identity": 0.37037500739097595, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/766b290af56b309649e253aa6195eb230f3d6e9e6e42e57499c981fad859afbb.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "767fd9cc79770654307a9241c50ee571df629c42ccea80b354757a9382b3c60a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "90bc07d444b7d8ceaaf184e6b5b12723d32fb166b02047cf5d933d77c7f6a3b8", "generation_seconds_batch": 20.30718487408012, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2628934383392334, "target_z": 1.406249975593088, "ce": 6.229123115539551, "genuineness": 4.444586753845215, "identity": 0.6721669435501099, "hypothesis": "La porte 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_Pleasure_Ecstasy/767fd9cc79770654307a9241c50ee571df629c42ccea80b354757a9382b3c60a.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "769eee37208f7f9e5ceb7a7a5df7203a92f4dc026fac1ac1e3bd56ce6105f103", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "18983167eb56f252d5554d835d7f6ea1cfcffb98a5afccfd30f3ea5868ea86cc", "generation_seconds_batch": 17.52212583797518, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09191527962684631, "target_z": -0.51171873474568, "ce": 6.252951145172119, "genuineness": 4.369274139404297, "identity": 0.7515466809272766, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/769eee37208f7f9e5ceb7a7a5df7203a92f4dc026fac1ac1e3bd56ce6105f103.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "76ce6e5b52ee6c973b40cb387dedf09672b865470e59edc6094f2ac7ec3e00a6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b977ae60be1e6aa2e6744b8511214a0e8404fbb4faab2958855dddd15b0c3de1", "generation_seconds_batch": 20.53882432798855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8980062007904053, "target_z": 0.8085938201698721, "ce": 6.173524379730225, "genuineness": 4.042920112609863, "identity": 0.6491697430610657, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/76ce6e5b52ee6c973b40cb387dedf09672b865470e59edc6094f2ac7ec3e00a6.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "76dfd821ed82e62dda4569a854934845e2c2223c17fd0aee189558f752c5884c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fecd6a35b973e1b7d7a58ef63fb7a7edc1b17a268f2f9b0ffa82af259577799d", "generation_seconds_batch": 20.30358464701567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7596828937530518, "target_z": 0.5820312896612321, "ce": 6.38003396987915, "genuineness": 4.143336772918701, "identity": 0.4696875810623169, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/76dfd821ed82e62dda4569a854934845e2c2223c17fd0aee189558f752c5884c.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "770d55170dbc253f0a1ba65de795e2c765012363a4aaac9526ccfff58df241e0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "45029f1ccc178b0f5dca9fc6ab1e58bd9695bab74c238928f7da56298297a526", "generation_seconds_batch": 23.684504356002435, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6356688737869263, "target_z": 0.37890622864395196, "ce": 6.284721851348877, "genuineness": 4.13078498840332, "identity": 0.7737187147140503, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/770d55170dbc253f0a1ba65de795e2c765012363a4aaac9526ccfff58df241e0.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": "77106027f92e2fab3aceb170005c170505b85323a1555b4f1e2aaf09eca83f45", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6329baa33ab82d97c81df4280147e6266cd6d04ca13c50d98fd5c4f503e44da0", "generation_seconds_batch": 15.962766260025091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18731063604354858, "target_z": -0.355468759152592, "ce": 6.284721851348877, "genuineness": 4.2374773025512695, "identity": 0.5446066856384277, "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_Pleasure_Ecstasy/77106027f92e2fab3aceb170005c170505b85323a1555b4f1e2aaf09eca83f45.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "779213bb8c35076ce6689cbb21f0eeaf40d0929f9e07f0c9e5cb7a2b9d72d86a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1541ec220e760c6b2e5ac64bd9b116fa858833bad4f228c2244b63da85de0a28", "generation_seconds_batch": 20.219810937996954, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4870725870132446, "target_z": 1.773437518305184, "ce": 6.149696350097656, "genuineness": 4.65797233581543, "identity": 0.5884031653404236, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/779213bb8c35076ce6689cbb21f0eeaf40d0929f9e07f0c9e5cb7a2b9d72d86a.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "9fe1575841b1cbf56a9127bd5fa2de44f3d6f402f8ba170b9403331a5b7ff165", "generation_seconds_batch": 15.250068085966632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5110586881637573, "target_z": 0.17480469588987602, "ce": 6.109982967376709, "genuineness": 4.406930446624756, "identity": 0.6283743977546692, "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_Pleasure_Ecstasy/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "779a8d834bb1a87fde01f8040e4d2c3b1dcc1a750aedfc9d688f9568353029da", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "2c1f5da6ad265cfbd5528c8000a415a8a7638e1c2cbf3376d5a9ff9d43150e1a", "generation_seconds_batch": 20.881617618026212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.000556230545044, "target_z": 0.9765625793224642, "ce": 5.7684478759765625, "genuineness": 4.074300289154053, "identity": 0.6173692345619202, "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_Pleasure_Ecstasy/779a8d834bb1a87fde01f8040e4d2c3b1dcc1a750aedfc9d688f9568353029da.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "781a1e4f5f649cb059b11776a51061d730cde8b00e70e46deef088cf984ab3a5", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "378a3fac5806c3373f601a789228119dc381c46843625e82dd1dfe153a658bcd", "generation_seconds_batch": 15.45686937100254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8765422105789185, "target_z": 0.773437518305184, "ce": 5.831989288330078, "genuineness": 3.785602569580078, "identity": 0.34330934286117554, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/781a1e4f5f649cb059b11776a51061d730cde8b00e70e46deef088cf984ab3a5.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": "78928f4ee0cadb5b96f9bb1609107568130596c0515af92d3ef95250ba06e15a", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "75b7ab8b9205ddacdaa5fa40f75d9406a828fedf6e60833fa5d9c2ceb2344930", "generation_seconds_batch": 22.716148340026848, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43831971287727356, "target_z": 0.055664063262716, "ce": 6.348263263702393, "genuineness": 4.262581825256348, "identity": 0.36814481019973755, "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_Pleasure_Ecstasy/78928f4ee0cadb5b96f9bb1609107568130596c0515af92d3ef95250ba06e15a.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "78f9d6df1d717d082ebfc7c36ee108a91b064c1db4eb39d60f7e055db969f988", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8b884de532aad33c5c591e37c2b2c6482f0ca2ec7f01d08f1ecba6cbc60bf628", "generation_seconds_batch": 21.5707573259715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4584540128707886, "target_z": 1.7265625793224642, "ce": 6.157639026641846, "genuineness": 4.293961524963379, "identity": 0.662011981010437, "hypothesis": "La porte 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_Pleasure_Ecstasy/78f9d6df1d717d082ebfc7c36ee108a91b064c1db4eb39d60f7e055db969f988.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "2db1d497c6132e093ac2513fc016d533633c23934e4fdbadb417e87f6e0906e0", "generation_seconds_batch": 15.25386576296296, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017983853816986084, "target_z": -0.632812506101728, "ce": 6.24500846862793, "genuineness": 4.362998008728027, "identity": 0.5691689252853394, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee als je weggaat.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "798c175780d1032773b6d991edfa211bf90c85e8e2b2ab3a072f467aae5e4a94", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "5dbd9e4b9edebd90054816bfbbeb06ff9d17649e5cb14e86ba77583bb602df8c", "generation_seconds_batch": 23.163376873009838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1102608442306519, "target_z": 1.156249975593088, "ce": 6.006728172302246, "genuineness": 4.507347106933594, "identity": 0.6450492143630981, "hypothesis": "La porte 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_Pleasure_Ecstasy/798c175780d1032773b6d991edfa211bf90c85e8e2b2ab3a072f467aae5e4a94.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "79f1e71f28ff003a952b88edc767611b88b0e1412b1c8001d98330658e4f3daa", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "385cbbab66a538957cfcdaa4ad9fe6facd51a977b2d4500b45350a1b160bc03f", "generation_seconds_batch": 17.560218233964406, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8717724084854126, "target_z": 0.7656249633896319, "ce": 6.356205940246582, "genuineness": 4.413206577301025, "identity": 0.4426443576812744, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/79f1e71f28ff003a952b88edc767611b88b0e1412b1c8001d98330658e4f3daa.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "7a125b13a40d989c05101b3647fe3d5f53d3cca78c764d20fe51ce60cbd5e6a7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8214cd4b315a9f7aa84bcd179edcdbc3e7854feda346be96a1ba68d6ffa72cd3", "generation_seconds_batch": 21.948647054028697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0355958938598633, "target_z": 2.671874890168896, "ce": 6.38003396987915, "genuineness": 4.268857479095459, "identity": 0.4552755653858185, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7a125b13a40d989c05101b3647fe3d5f53d3cca78c764d20fe51ce60cbd5e6a7.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "7a42a41fde08e87087919760daea5a4886e8237892f9dfe0ced53d75360176bf", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1132d93e59aaead17f6a8e648e3841d4867ab3adfba6ebaeff43e024b2c3fe3d", "generation_seconds_batch": 21.136422121082433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8288445472717285, "target_z": 0.6953125549155521, "ce": 6.221180438995361, "genuineness": 4.017816066741943, "identity": 0.4768468141555786, "hypothesis": "The 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_Pleasure_Ecstasy/7a42a41fde08e87087919760daea5a4886e8237892f9dfe0ced53d75360176bf.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "7a77a8d195b605353fb0788b65207cfe40fc5ee23fe94cebe64b1fa628ffbfdf", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3830f500462163fefe7ea8d0fd96e5311f152a42f8cfa70e5004726848aa7e81", "generation_seconds_batch": 19.94707086600829, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.5888891220092773, "target_z": 3.578125012203456, "ce": 5.927301406860352, "genuineness": 3.9676074981689453, "identity": 0.49138104915618896, "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_Pleasure_Ecstasy/7a77a8d195b605353fb0788b65207cfe40fc5ee23fe94cebe64b1fa628ffbfdf.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "7a7c72c06a68c20879806094807d3c66dd3d2411c08da7bb96b46a702c8df642", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "05ac3571ed60ad0db4f902519d5bf18423476d80b31cef100edcfe6c6c15f7a3", "generation_seconds_batch": 22.00282302906271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6964834332466125, "target_z": 0.478515620423704, "ce": 6.213237762451172, "genuineness": 4.406930446624756, "identity": 0.35658901929855347, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7a7c72c06a68c20879806094807d3c66dd3d2411c08da7bb96b46a702c8df642.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "7a7fabf27bb0a5b8a27df2e614d2a61c78966e63b4c4bca10eec671006964384", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d53d0d95e3f984bc3d1846899b08a8dbc27e75acbb1f63705f0b57d75c96dc7", "generation_seconds_batch": 21.01279872097075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3487492799758911, "target_z": 1.546874987796544, "ce": 5.895530700683594, "genuineness": 3.528284788131714, "identity": 0.465848833322525, "hypothesis": "The 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_Pleasure_Ecstasy/7a7fabf27bb0a5b8a27df2e614d2a61c78966e63b4c4bca10eec671006964384.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "7bcfbe32823d28c9a0f2c822eb53d3540cde91dfaaf8accaba7120b63eb6aac7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "75c9c654b207517b315c82df97d2f4bdcab627bb87268339eb6a40dc7c583080", "generation_seconds_batch": 20.771472625085153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.051372230052948, "target_z": -0.578125012203456, "ce": 6.149696350097656, "genuineness": 4.532451152801514, "identity": 0.8138771057128906, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7bcfbe32823d28c9a0f2c822eb53d3540cde91dfaaf8accaba7120b63eb6aac7.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "7c3668437c9dc997c14c26ed5a340f3853a7e0f16a0744eb3b6e471148974989", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "33091f53c8c8290200ba1231960dd68490fecc491b043d733c7287c5ce8f3a00", "generation_seconds_batch": 20.881617618026212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1770375967025757, "target_z": 1.265624963389632, "ce": 6.09409761428833, "genuineness": 4.21237325668335, "identity": 0.551396906375885, "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_Pleasure_Ecstasy/7c3668437c9dc997c14c26ed5a340f3853a7e0f16a0744eb3b6e471148974989.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "7c778432ce0e3a4d35b7c3410787d06db0041c9cb8e52a02313972d4901f3883", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "90d73e305041a37ce0439a056a29bf31a9b65794e5dc6205efc1d116b3c5cc96", "generation_seconds_batch": 20.544263600022532, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6702497005462646, "target_z": 0.435546861271112, "ce": 6.308549880981445, "genuineness": 4.231201171875, "identity": 0.5793329477310181, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7c778432ce0e3a4d35b7c3410787d06db0041c9cb8e52a02313972d4901f3883.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "7ccf2625a61524cf99d9513b3addd8c2460d5e4ebd1b6a403043b955c88b6828", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3106277a0fb3ed0b048a5ba07bae7d96cdd91538d0be5a421aa7827fb83bbbb3", "generation_seconds_batch": 20.684196892078035, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6070502996444702, "target_z": 0.3320312896612321, "ce": 6.372091293334961, "genuineness": 4.457139015197754, "identity": 0.33604949712753296, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7ccf2625a61524cf99d9513b3addd8c2460d5e4ebd1b6a403043b955c88b6828.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "7d91d9b52b44648d42d12dd6ba5e1e0e66c18b7bab8c3ad9fadb8be322e48ab9", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6531eb77bf39f219297834b398d13602e41297bc62dd651083e4018055369a93", "generation_seconds_batch": 15.914144921931438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3827221095561981, "target_z": -0.03540037098506297, "ce": 5.95112943649292, "genuineness": 4.168440818786621, "identity": 0.3723955452442169, "hypothesis": "De deur 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_Pleasure_Ecstasy/7d91d9b52b44648d42d12dd6ba5e1e0e66c18b7bab8c3ad9fadb8be322e48ab9.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "7d970b74cd781fe2376477383ed2e96c5bc6854e9d4ef5c161a5c03b5abae8e0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d7dde2f5e3884c6b362fee3a7e48bce452536597a55bb05b0e0223a1695b55d6", "generation_seconds_batch": 20.04060266003944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9600131511688232, "target_z": 0.910156253050864, "ce": 6.24500846862793, "genuineness": 4.344170093536377, "identity": 0.7198666334152222, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7d970b74cd781fe2376477383ed2e96c5bc6854e9d4ef5c161a5c03b5abae8e0.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "7de27fd905e08ba9d0f2eec30b47b72d0548466131b20e330e8939fb308a5597", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5e70fa4967bad01e0e742369a814f018810bdef8beb54b50d69d0bc5d796bdf1", "generation_seconds_batch": 17.855591668980196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9504736661911011, "target_z": 0.8945313384750562, "ce": 6.197352409362793, "genuineness": 4.413206577301025, "identity": 0.6750503182411194, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7de27fd905e08ba9d0f2eec30b47b72d0548466131b20e330e8939fb308a5597.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "7e127bc3a0dabf41a2ee27858ad5328b78cddedb451b9f35c53f02935f571b3f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "46c5220dff9b93cbce47a3f531783f979637011a3982b0832619fbf614b24b33", "generation_seconds_batch": 21.593442999990657, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5633889436721802, "target_z": 1.8984376159328322, "ce": 6.078212261199951, "genuineness": 4.413206577301025, "identity": 0.6060802936553955, "hypothesis": "La porte 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_Pleasure_Ecstasy/7e127bc3a0dabf41a2ee27858ad5328b78cddedb451b9f35c53f02935f571b3f.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "7ebee0bbbbab5026553c4a69c4622995d9328e36262ff07642d076a4090642d5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3efcf8f7845954dfcb7e0741f15142792721a99573296781f7a85a6d25b52114", "generation_seconds_batch": 23.463221274898387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.692172646522522, "target_z": 2.109375036610368, "ce": 6.109982967376709, "genuineness": 4.049196243286133, "identity": 0.5607925653457642, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7ebee0bbbbab5026553c4a69c4622995d9328e36262ff07642d076a4090642d5.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "7f05ad8f983e7adabf6e63bfd38c0faaeb426d98e0c92cedbdb55623ed5c4c5d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "848d3679ab4ad5203fba7136880503ac5bbc815173fae36920ca53037f6c18ed", "generation_seconds_batch": 20.379085892927833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5872377157211304, "target_z": 1.9375, "ce": 6.197352409362793, "genuineness": 4.262581825256348, "identity": 0.3936993479728699, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7f05ad8f983e7adabf6e63bfd38c0faaeb426d98e0c92cedbdb55623ed5c4c5d.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "7f422ce1021efaf94a071e204589f82c99c54d6f964e1e297ea2bf932c90ebee", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bd7eebf59b54e4066835964a6ceb33340c91d8b8c3c47ee8049868d2f0bd0537", "generation_seconds_batch": 17.62727914901916, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.644474983215332, "target_z": 2.031250073220736, "ce": 6.1894097328186035, "genuineness": 4.570107460021973, "identity": 0.6116173267364502, "hypothesis": "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_Pleasure_Ecstasy/7f422ce1021efaf94a071e204589f82c99c54d6f964e1e297ea2bf932c90ebee.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "2e77e0a9013450bdabe69275023f47c0fcd575799fcf489690e3338a206be1b0", "generation_seconds_batch": 17.065223688958213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4651496708393097, "target_z": 0.09960939177975203, "ce": 6.427689552307129, "genuineness": 4.545003414154053, "identity": 0.40073952078819275, "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_Pleasure_Ecstasy/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "7f828f11a63801fd540680c916955ebe4c584477c730f0d2533a43505b62445f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6618aa1aa34e47d368daf4b6bc20c5ba224b522b3a96a06f895cb2182c807c5f", "generation_seconds_batch": 20.33810295094736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9020425081253052, "target_z": 2.453125109831104, "ce": 6.157639026641846, "genuineness": 4.394378662109375, "identity": 0.2737159729003906, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7f828f11a63801fd540680c916955ebe4c584477c730f0d2533a43505b62445f.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "7f9a320286acb95ecde0716c97045bf81f8861d29b26cf6d27027ee141c10453", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ece8d9a88ed70cc5b838a46e5142e584dbbac0882a0dd8a19e262e24a8d73e02", "generation_seconds_batch": 21.458389966050163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9313945770263672, "target_z": 0.8632813140681441, "ce": 6.173524379730225, "genuineness": 4.18726921081543, "identity": 0.30459874868392944, "hypothesis": "The 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_Pleasure_Ecstasy/7f9a320286acb95ecde0716c97045bf81f8861d29b26cf6d27027ee141c10453.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "7fba6d8c16b820c0448771fb5bb6abfa33738a01f6c15c85410d7c4691aeae97", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7b47079aae85a58e12012332bfe39f6cab04cda1b1dbcf3bcf48aa0b06e60abc", "generation_seconds_batch": 19.554542625905015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7112517356872559, "target_z": 2.14062506101728, "ce": 6.467403411865234, "genuineness": 3.973883628845215, "identity": 0.5116404294967651, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7fba6d8c16b820c0448771fb5bb6abfa33738a01f6c15c85410d7c4691aeae97.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "7fda1b2098cce7986eeaf3f5ac162b9a3eec981ced8ef76470aeb09e11d825a3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "654482f0c92ae94c129194bf4f9f0c992dbf8e552642c9438d4c1c897437194c", "generation_seconds_batch": 21.261153049068525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7303308248519897, "target_z": 2.171875085424192, "ce": 6.38797664642334, "genuineness": 4.369274139404297, "identity": 0.5240733623504639, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/7fda1b2098cce7986eeaf3f5ac162b9a3eec981ced8ef76470aeb09e11d825a3.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "7fe348d6eb3ebe3de703364dc9619c2ac17703b8e2289660d12e13589a642155", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4b450326904c50eca81ea759a146c09a2e15883205c5e05f53a37acc05d0e18a", "generation_seconds_batch": 16.70598308404442, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.967167854309082, "target_z": 0.9218750854241922, "ce": 6.221180438995361, "genuineness": 3.9299514293670654, "identity": 0.2777026295661926, "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_Pleasure_Ecstasy/7fe348d6eb3ebe3de703364dc9619c2ac17703b8e2289660d12e13589a642155.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "8040b894c73ecf04ce1ca5b732192519152431504e5c40b55d433cee0dea4347", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "fb9ba83df56323592e08cf0540cf6c6d9dde4e3cf81b458f9bde76071a50c805", "generation_seconds_batch": 17.01019164500758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6678647994995117, "target_z": 0.4316405838133359, "ce": 6.38003396987915, "genuineness": 4.507347106933594, "identity": 0.5608565807342529, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8040b894c73ecf04ce1ca5b732192519152431504e5c40b55d433cee0dea4347.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "806590daf1551aea6fad1c80602316a221611ab67c8a17b7c2e61806f9fd9732", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0b3a54695f6e33642f358045e8399fa9b2bc44da1b1684d251d5039c299acec1", "generation_seconds_batch": 19.686490372987464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0029410123825073, "target_z": 0.9804686615249438, "ce": 6.1020402908325195, "genuineness": 3.835810661315918, "identity": 0.4237520694732666, "hypothesis": "The 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_Pleasure_Ecstasy/806590daf1551aea6fad1c80602316a221611ab67c8a17b7c2e61806f9fd9732.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "f410831954b03621c15d5e4bb7da9108f96af0787fb39ce8a363cbf406f83976", "generation_seconds_batch": 15.256656678044237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.205197274684906, "target_z": -0.326171873474568, "ce": 6.268836498260498, "genuineness": 3.9425034523010254, "identity": 0.6634160280227661, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana. Llévatelas cuando te vayas.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "8119c492d68448da5b54498546e77bfe6b8027c84ee5b6338d64066b38381689", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "36225f4a0bf18d58569a2081bab91400acf06ad4c4c5eb290ccda5440111b57e", "generation_seconds_batch": 19.54217707097996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4346051216125488, "target_z": 1.6875, "ce": 6.308549880981445, "genuineness": 4.425758361816406, "identity": 0.5311586856842041, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8119c492d68448da5b54498546e77bfe6b8027c84ee5b6338d64066b38381689.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "815cc0ac5c1eecad1679b304b7f4106863427b36d7cc8bbef8cae9759e62521c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1a50ff9075e6c180670a8300a6a50d5c4899728425c69faadbf891ec481b5078", "generation_seconds_batch": 19.22687830403447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9027758836746216, "target_z": 0.8164061798301279, "ce": 6.006728172302246, "genuineness": 4.2751336097717285, "identity": 0.5004969239234924, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/815cc0ac5c1eecad1679b304b7f4106863427b36d7cc8bbef8cae9759e62521c.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": "81dbcdc24a618e0301f6b443f06ffaa0a63dff7b98fdc13d893a418bb65419f2", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "adce88c728763fc804aefb6e6a9326e50c8303cb0e0961d4fee11e0a88514aaf", "generation_seconds_batch": 17.251630749902688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36170530319213867, "target_z": -0.069824221419506, "ce": 6.356205940246582, "genuineness": 4.457139015197754, "identity": 0.5675170421600342, "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_Pleasure_Ecstasy/81dbcdc24a618e0301f6b443f06ffaa0a63dff7b98fdc13d893a418bb65419f2.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "81f12b0eecb8732cfd98be35b7f9f6715324b91bbfb7cd04c7955dfe98fd16da", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "19bb1149a05facc02ddc3cf2675550292e37e42d87567ca0ed0c02d1006bd20a", "generation_seconds_batch": 19.562309146975167, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5586191415786743, "target_z": 1.8906250610172801, "ce": 6.23706579208374, "genuineness": 4.444586753845215, "identity": 0.507814347743988, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/81f12b0eecb8732cfd98be35b7f9f6715324b91bbfb7cd04c7955dfe98fd16da.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "824920004d1d6cbeb01aba994a739de2c5443b826ee7bff5d2abc463e21027bb", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "10fb75804953205823c55ec5e86ef99629cda421b24aad92423091e6103f4d7c", "generation_seconds_batch": 20.42283347598277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33845269680023193, "target_z": -0.10791013374987797, "ce": 6.197352409362793, "genuineness": 4.432034492492676, "identity": 0.7388988137245178, "hypothesis": "De nuur 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_Pleasure_Ecstasy/824920004d1d6cbeb01aba994a739de2c5443b826ee7bff5d2abc463e21027bb.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": "825895a352b0b9eae8e43a8a9423953bec630794b0f2486e4598ee23fe66a6b8", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c64dbc1b2fb5c0f7f1d987feb8b8dff629ad7a94c8d412c743b4c8e6a5447c16", "generation_seconds_batch": 16.120293727028184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45203280448913574, "target_z": 0.07812501220345602, "ce": 6.475345611572266, "genuineness": 4.7332844734191895, "identity": 0.4298432767391205, "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_Pleasure_Ecstasy/825895a352b0b9eae8e43a8a9423953bec630794b0f2486e4598ee23fe66a6b8.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "836d091af42d9bbd3abefec5b55190f8ec0e2ed459c7cd872fdb45e926144756", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "32ba108d3d8786de17f8de5f58f6b4f4833db04d550bcb3ed5fc3943f1f9cc0f", "generation_seconds_batch": 21.403481506975368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8352657556533813, "target_z": 2.3437501220345602, "ce": 6.213237762451172, "genuineness": 4.507347106933594, "identity": 0.5198277831077576, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/836d091af42d9bbd3abefec5b55190f8ec0e2ed459c7cd872fdb45e926144756.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "83af52632d7129a67393912df74599b569a23daa86be88689ab126f570e92ef3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ed0316c1850c257a5496205ef82a7b37b7f446022c092a2d3b09ed51caaffe25", "generation_seconds_batch": 20.657300467020832, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.07687246799469, "target_z": 1.101562481694816, "ce": 6.157639026641846, "genuineness": 4.093128204345703, "identity": 0.5992028713226318, "hypothesis": "La porte 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_Pleasure_Ecstasy/83af52632d7129a67393912df74599b569a23daa86be88689ab126f570e92ef3.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "847fe3d6f0f5b6be54c2b6c017cedd3411e0bee91184ba5b00438c67bdfb4747", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d6eb82eb785a39993cf96340dddce032213fe7ef858563ba51bfeb0f2b3cbbcf", "generation_seconds_batch": 19.242013599956408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.072102665901184, "target_z": 1.0937499267792639, "ce": 6.109982967376709, "genuineness": 3.8169827461242676, "identity": 0.5638256669044495, "hypothesis": "The 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_Pleasure_Ecstasy/847fe3d6f0f5b6be54c2b6c017cedd3411e0bee91184ba5b00438c67bdfb4747.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "84cbfc8a8d596921f5eaea47563dca679d565b7a6055c4c7d532b4036c20c69a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "847e6fdeb8274aac1e9bf1703653fd9752af8ec23710957775d60c105f5cea01", "generation_seconds_batch": 21.402558127068914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.102372646331787, "target_z": 2.7812498779654398, "ce": 6.181467056274414, "genuineness": 4.143336772918701, "identity": 0.4738651216030121, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/84cbfc8a8d596921f5eaea47563dca679d565b7a6055c4c7d532b4036c20c69a.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": "84d1d2363a17bee4a9108c01c1bf35cb2790652f1e614a226862726748306010", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "703cae9a4c9c5f978bda6d5f530ade52f63bf5d2c552b813a9901ad4621e7314", "generation_seconds_batch": 17.788708267034963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0029410123825073, "target_z": 0.9804686615249438, "ce": 6.260893821716309, "genuineness": 4.281409740447998, "identity": 0.6612709164619446, "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_Pleasure_Ecstasy/84d1d2363a17bee4a9108c01c1bf35cb2790652f1e614a226862726748306010.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "84e8d3dd67f2a42a693f9120c37d6ee6229890cd984c017f1b8397b922212374", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dbaf52dd1fe098c5a4582a15cc1f56c153fc0099ce64784a9b50686fedf135b0", "generation_seconds_batch": 20.839750748942606, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5872377157211304, "target_z": 1.9375, "ce": 6.38003396987915, "genuineness": 4.419482707977295, "identity": 0.7466192841529846, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/84e8d3dd67f2a42a693f9120c37d6ee6229890cd984c017f1b8397b922212374.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "854384fef0bc58dd58ec58f459f37b02372bc857e7985be40ba8838715c03a0a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "88f741c351d8a1b076f68b6bf9c614b202ce4d0eb926bb3c9a1314ba0f48f776", "generation_seconds_batch": 22.402936437050812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6571328639984131, "target_z": 0.41406253050864006, "ce": 6.165581703186035, "genuineness": 4.21237325668335, "identity": 0.5691483616828918, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/854384fef0bc58dd58ec58f459f37b02372bc857e7985be40ba8838715c03a0a.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "85dda145e1f049ededb629ffc7e0fd06f58665db970c8896798ff1e3db65355f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6516db187c5c4554ad83edc87e8ddb1f076d7cdf68b769d82ea081f79c4a68a9", "generation_seconds_batch": 20.72856266796589, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.091181755065918, "target_z": 1.124999951186176, "ce": 6.054384231567383, "genuineness": 4.306513786315918, "identity": 0.29370975494384766, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/85dda145e1f049ededb629ffc7e0fd06f58665db970c8896798ff1e3db65355f.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "860979bd3df7e322aa6954b318a05936e3eb7044f1a8cd65fa8e8dc6a8847ee4", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d19192a5074577d7edfcd5fa593c8549cdbca0571dae27ddd77fd038a2f33097", "generation_seconds_batch": 18.46147519396618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.968819260597229, "target_z": 2.562500097627648, "ce": 5.514282703399658, "genuineness": 4.582659721374512, "identity": 0.3491787314414978, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/860979bd3df7e322aa6954b318a05936e3eb7044f1a8cd65fa8e8dc6a8847ee4.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "86615b0467ab0ae76e1c2bb93efe9d52662e922c890753761c4b94e63f5fde67", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f08607c2bfd04af643cbd80d94e48dd0181e590c94da215a90a0424340b64b48", "generation_seconds_batch": 20.176805865950882, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.967167854309082, "target_z": 0.9218750854241922, "ce": 6.109982967376709, "genuineness": 4.419482707977295, "identity": 0.73255455493927, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/86615b0467ab0ae76e1c2bb93efe9d52662e922c890753761c4b94e63f5fde67.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "8687a536c24f035005114a6c572b30d92334f653ce57096c1677d4e2d6e850e3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "49b62e3b94396cc48a3d9cfc05c15e22a4dfd22334dcae41ed0d28d75accc000", "generation_seconds_batch": 22.149887103005312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6540144681930542, "target_z": 2.046874987796544, "ce": 5.990842819213867, "genuineness": 4.218649387359619, "identity": 0.4756752848625183, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8687a536c24f035005114a6c572b30d92334f653ce57096c1677d4e2d6e850e3.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "872502e8706c1ac03c0e9f2905ac82430e6cfbd62c930388a7514b0670c4760b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d7dc103cd337afba06a032f6bb39e059658b5f10973c0b6aed7dc01d468b3081", "generation_seconds_batch": 20.41927737905644, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.367828369140625, "target_z": 1.578125012203456, "ce": 5.879645347595215, "genuineness": 4.2249250411987305, "identity": 0.5153976678848267, "hypothesis": "The door is still open. I put your code on the chair to help me when you are ready.", "wer": 0.16666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/872502e8706c1ac03c0e9f2905ac82430e6cfbd62c930388a7514b0670c4760b.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "87698e3b2570e8f4abb7dc9676b9f0dcc7157b8ac9ae24835906433687ea9746", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "cf33ac96540381be31c6bbd1032b46136fb84ca57e84204589b0defe5dcbacdd", "generation_seconds_batch": 19.83518573397305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24931763112545013, "target_z": -0.253906253050864, "ce": 6.0305562019348145, "genuineness": 4.325342178344727, "identity": 0.11943100392818451, "hypothesis": "De deur 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_Pleasure_Ecstasy/87698e3b2570e8f4abb7dc9676b9f0dcc7157b8ac9ae24835906433687ea9746.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "8787f92ac0d12c64ec8e59fddfc911ada8fa0871498679997c8031efde42e68c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "736d1bf894265cf5a6edf194fbb4d457e01b128e5d4ac6a7a66ce3bc50789acc", "generation_seconds_batch": 16.906033062026836, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.8846147060394287, "target_z": 4.062499902372352, "ce": 5.792276382446289, "genuineness": 3.873466968536377, "identity": 0.412760853767395, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8787f92ac0d12c64ec8e59fddfc911ada8fa0871498679997c8031efde42e68c.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "87dc9765521929a71f50de0663b95c82849bd3fc30c4a9eb04da2ef1b015febd", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "675364df94f133b7d5bc880514f906e1a7f0ac04640eb94d62971717f7b62397", "generation_seconds_batch": 20.711381254019216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6349353790283203, "target_z": 2.015624963389632, "ce": 6.356205940246582, "genuineness": 4.281409740447998, "identity": 0.6226477026939392, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/87dc9765521929a71f50de0663b95c82849bd3fc30c4a9eb04da2ef1b015febd.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "885146758900a45cc1d2d9ff61ce758e84c39773ad47f38892244f391e18a507", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "11c957799968521f42e82935dcc6d44510d94077431ef2fd39a0128214a30a28", "generation_seconds_batch": 20.670540262013674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6297066807746887, "target_z": 0.36914063262716, "ce": 6.332377910614014, "genuineness": 3.9550557136535645, "identity": 0.43429434299468994, "hypothesis": "The 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_Pleasure_Ecstasy/885146758900a45cc1d2d9ff61ce758e84c39773ad47f38892244f391e18a507.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "886c2c1eba2b54b4d56b15fb7c9faff896a98266ff38a4cb91172cbb47f31de2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c274d2490c4ce882cacf894fc7ee3c4355f68537dc1b9f76b0459ef10fdbbe22", "generation_seconds_batch": 19.219897122005932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1102608442306519, "target_z": 1.156249975593088, "ce": 6.133810997009277, "genuineness": 4.21237325668335, "identity": 0.5804381370544434, "hypothesis": "La porte 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_Pleasure_Ecstasy/886c2c1eba2b54b4d56b15fb7c9faff896a98266ff38a4cb91172cbb47f31de2.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": "889dcdb30bbd23e48a369ec96a1817266ab3171f6ff72ec5f0ad16be3ec466e7", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "140401d8201af740826b4abcc3f57218ca4c58c2ba4b66609f249dce218eb528", "generation_seconds_batch": 15.960129579994828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6583253145217896, "target_z": 0.4160156692375281, "ce": 6.229123115539551, "genuineness": 4.68307638168335, "identity": 0.5408890247344971, "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_Pleasure_Ecstasy/889dcdb30bbd23e48a369ec96a1817266ab3171f6ff72ec5f0ad16be3ec466e7.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "88b420a7aa202d855745f9d554c369f151821fd60051be15192dd575d54f6113", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "9c742a1b25901c55bbc47a1819d0458893ad142dd85d37991834a5111febff0f", "generation_seconds_batch": 17.094967384939082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1944652944803238, "target_z": -0.34375, "ce": 5.9431867599487305, "genuineness": 4.218649387359619, "identity": 0.5343751907348633, "hypothesis": "De deur 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_Pleasure_Ecstasy/88b420a7aa202d855745f9d554c369f151821fd60051be15192dd575d54f6113.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "88bbe2228a7a31a66026d92c10cf414c49edf548af3f9aa46e6442d5926fdad9", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "203d0e48e08cca8911da4aa5b57afb8a6e29d927a214a0a3665992e20e3667ed", "generation_seconds_batch": 15.370196218951605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8121503591537476, "target_z": 0.6679688079664161, "ce": 6.109982967376709, "genuineness": 4.3504462242126465, "identity": 0.5566179752349854, "hypothesis": "La porte 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_Pleasure_Ecstasy/88bbe2228a7a31a66026d92c10cf414c49edf548af3f9aa46e6442d5926fdad9.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "88c20a0c52383be5067ec86ad677d58a5fc4b45fac0c9f36e217a775940c8846", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "59a52755772a530dfa40b6f71231b9f06b53ff02b24faf9a7388c95884040837", "generation_seconds_batch": 16.552942053996958, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2008864879608154, "target_z": 1.304687542712096, "ce": 6.260893821716309, "genuineness": 4.532451152801514, "identity": 0.7458073496818542, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/88c20a0c52383be5067ec86ad677d58a5fc4b45fac0c9f36e217a775940c8846.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "88e8438f66754d1d571c580066dade34c98ad80774018978b7d0960d242df56b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "107ea9a6cf38de1e803f2403528c7323e5fb153e877b9cb59f91ab840069a893", "generation_seconds_batch": 19.975617483025417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1245701313018799, "target_z": 1.179687445084448, "ce": 6.09409761428833, "genuineness": 4.049196243286133, "identity": 0.5323908925056458, "hypothesis": "The 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_Pleasure_Ecstasy/88e8438f66754d1d571c580066dade34c98ad80774018978b7d0960d242df56b.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "8915d12a8977cba9df7fcff104b4c0b27bc652264508e40f6d0ba0b973ac330e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "533f232b933d4c15a0c812a1e0662f97ff427e10cbee804a9c6f10145f81a81d", "generation_seconds_batch": 20.33810295094736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8352657556533813, "target_z": 2.3437501220345602, "ce": 6.141753673553467, "genuineness": 4.300237655639648, "identity": 0.31639912724494934, "hypothesis": "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_Pleasure_Ecstasy/8915d12a8977cba9df7fcff104b4c0b27bc652264508e40f6d0ba0b973ac330e.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "8974ef8d94742681cb60928e0f52c1e0d2dc627c1cce4a3d536ce1422e9392c7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ad68f8429ca21854c9f48ce58d45a0cec4754b0efc9962272f4c5cf5ff5d5424", "generation_seconds_batch": 21.086857776041143, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8622329235076904, "target_z": 0.7500000488138241, "ce": 6.221180438995361, "genuineness": 4.118232727050781, "identity": 0.18488295376300812, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8974ef8d94742681cb60928e0f52c1e0d2dc627c1cce4a3d536ce1422e9392c7.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "89fb35915451113310a7b34087caf23ab558f88b6da68acc30acca85200b9ff8", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d61e0da2f5bbd8793464bfedc32413db81af68098d5eebfa411b82ab23dcb716", "generation_seconds_batch": 21.106062615057454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9020425081253052, "target_z": 2.453125109831104, "ce": 5.967014789581299, "genuineness": 4.055472373962402, "identity": 0.7040672302246094, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/89fb35915451113310a7b34087caf23ab558f88b6da68acc30acca85200b9ff8.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "8a4dfe5fb559206c226417391cf6825b5669e13e15f7523ca789b87709f1fed0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b5da54845e9270f630383d45441476e06a64d6207724207064545ea2fc03b22d", "generation_seconds_batch": 15.616663867025636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6110866069793701, "target_z": 1.9765625793224642, "ce": 6.24500846862793, "genuineness": 4.3881025314331055, "identity": 0.1033557578921318, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8a4dfe5fb559206c226417391cf6825b5669e13e15f7523ca789b87709f1fed0.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "8aa88b8abf250f25024bcfacd7a2eb01cccc84b0d2b1b2d3d21ed25e61cad307", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8e27f302aa73ee81bb90a32795bc51d040fc8841f8fe2d24a56f5521f45a0373", "generation_seconds_batch": 22.757509530056268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.396446943283081, "target_z": 1.624999951186176, "ce": 6.340320587158203, "genuineness": 4.268857479095459, "identity": 0.6002273559570312, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8aa88b8abf250f25024bcfacd7a2eb01cccc84b0d2b1b2d3d21ed25e61cad307.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": "8aba82ca037542e22c43916507929aa4dc0bfbb8a0b534f32c2e764aec367ae0", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7c3eb5a601792adc74144ef8ba032363b3f0f13abdac5056fcf255d02308c4af", "generation_seconds_batch": 16.209773445967585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2123519331216812, "target_z": -0.314453114321976, "ce": 6.173524379730225, "genuineness": 3.9676074981689453, "identity": 0.4022575616836548, "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_Pleasure_Ecstasy/8aba82ca037542e22c43916507929aa4dc0bfbb8a0b534f32c2e764aec367ae0.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "8b10c0cc823b88d56d88cc12fc88888a6707997bfb0f9276365acb70d268f77b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "2e019761962e9164ff039c70d0388412ad7e0accb007cbb0b52f1e8017b7ba6f", "generation_seconds_batch": 20.376117357984185, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1882286071777344, "target_z": 2.921875085424192, "ce": 5.43088436126709, "genuineness": 3.9173994064331055, "identity": 0.5664975643157959, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8b10c0cc823b88d56d88cc12fc88888a6707997bfb0f9276365acb70d268f77b.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "8b1e008305fcab42418142a21bfdbe35d3dc8d155f8ae6736578300e09ba5bd3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6ecdd686c1c8ed351c34a5c200236421d52fd5d5494a39dbdaee7584c0c82119", "generation_seconds_batch": 22.112029579933733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1531888246536255, "target_z": 1.2265625793224642, "ce": 6.3641486167907715, "genuineness": 3.8671910762786865, "identity": 0.3636268377304077, "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_Pleasure_Ecstasy/8b1e008305fcab42418142a21bfdbe35d3dc8d155f8ae6736578300e09ba5bd3.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "8c2dc07910b24bf4c77884f097ed55f8ea0e78fa90d033f41b1ee7d942672371", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "30c948c3e286c9e789634d17b0a4256a30fea54946ebdd401253c868107f793f", "generation_seconds_batch": 15.023210840066895, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3980982303619385, "target_z": 3.2656247681343356, "ce": 5.744620323181152, "genuineness": 3.9801597595214844, "identity": 0.45726242661476135, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8c2dc07910b24bf4c77884f097ed55f8ea0e78fa90d033f41b1ee7d942672371.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "8c3a279c24c946ac2646101b2725d56f04f6974eb3895686e6797aa83442c362", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "13a5abaa04726874010c9aa8514483b95ea261791c306929a288790b04131126", "generation_seconds_batch": 19.618075890932232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1198004484176636, "target_z": 1.1718750854241922, "ce": 5.919358730316162, "genuineness": 3.7667744159698486, "identity": 0.4723213315010071, "hypothesis": "The 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_Pleasure_Ecstasy/8c3a279c24c946ac2646101b2725d56f04f6974eb3895686e6797aa83442c362.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "8cb05090684c2632b56b9e55272ee22759eed4952528ef2c95ffba28a53c9127", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8d46aea666c1a7b275922b3b9ca0b410812cb5879083851740809794598ad6cd", "generation_seconds_batch": 20.745537851005793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6063168048858643, "target_z": 1.968750024406912, "ce": 6.117925643920898, "genuineness": 3.9550557136535645, "identity": 0.12306538224220276, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8cb05090684c2632b56b9e55272ee22759eed4952528ef2c95ffba28a53c9127.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "8cb2cdba636bb65417c4d145a5611c05091bd000c2d0e701a09fe2c4c1ffc407", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "53cae0a11ac0d11f18ec11fa5b09e28cf2cdc94d236368804dff12bc1149743f", "generation_seconds_batch": 19.33615984302014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.012480616569519, "target_z": 0.996093771356048, "ce": 6.435632705688477, "genuineness": 3.9801597595214844, "identity": 0.40617457032203674, "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_Pleasure_Ecstasy/8cb2cdba636bb65417c4d145a5611c05091bd000c2d0e701a09fe2c4c1ffc407.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "8cb7c151e3439f4aec2365c91ec089f997683086e708bdc7bb7278b99032ee98", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6f3af104731d45d2ea8078f517d8b21b6c6b57b17b9415c31dba0fff0bae8d38", "generation_seconds_batch": 20.72856266796589, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7835317254066467, "target_z": 0.621093771356048, "ce": 6.252951145172119, "genuineness": 4.545003414154053, "identity": 0.4836844503879547, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8cb7c151e3439f4aec2365c91ec089f997683086e708bdc7bb7278b99032ee98.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "8cb7dc41bb1b331c89b517eb4dd58500dc93e41fd762035bd79052bdc8930290", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "92a65b40c97327b05fd27550df99dea0c443ea641abb6d4311e4e56d4847c5c8", "generation_seconds_batch": 20.771472625085153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3869701623916626, "target_z": -0.028442399687591526, "ce": 6.09409761428833, "genuineness": 4.287685871124268, "identity": 0.4179256856441498, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg, maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8cb7dc41bb1b331c89b517eb4dd58500dc93e41fd762035bd79052bdc8930290.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "8cbee9651037e78d4c20203349d812af5a1e29980c0218cc013b79ea2c222d4a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "394cbb356beb3642bb5124109c988992cfe1c3e1fbd24403b379c5499e864f42", "generation_seconds_batch": 20.93038004799746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.138879418373108, "target_z": 1.2031249145758078, "ce": 5.959072113037109, "genuineness": 4.18099308013916, "identity": 0.5519257187843323, "hypothesis": "La porte 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_Pleasure_Ecstasy/8cbee9651037e78d4c20203349d812af5a1e29980c0218cc013b79ea2c222d4a.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "8cbff1cc8d046ffff517b9374b2ab16b73dba2771d6a8c2a55bc07b388fc74da", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "48a4cbe9ea2cd103108d68e3d59a874af46c10a273eb36c40d4e1cf3dc34d2d4", "generation_seconds_batch": 20.93038004799746, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5681586265563965, "target_z": 1.906249975593088, "ce": 6.260893821716309, "genuineness": 4.2249250411987305, "identity": 0.48341232538223267, "hypothesis": "La porte 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_Pleasure_Ecstasy/8cbff1cc8d046ffff517b9374b2ab16b73dba2771d6a8c2a55bc07b388fc74da.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "8dedcd72930175d8d002dffb77d3baac4148d90129dc8c5e91f425db4dfcb0f2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e55c2c43df5b1894825ca01d0f39deb60f407db3d1154a276dc70f3ddb293662", "generation_seconds_batch": 21.742345917969942, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4113779664039612, "target_z": 0.011535634091574733, "ce": 6.356205940246582, "genuineness": 4.7081804275512695, "identity": 0.6919173002243042, "hypothesis": "Ja, ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen daar samen in kijken.", "wer": 0.1111111111111111, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8dedcd72930175d8d002dffb77d3baac4148d90129dc8c5e91f425db4dfcb0f2.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "8ee27067a2a9dda9321b113f385919abf7cf057a5af5131f6883daafb7c44a28", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8b3c22c1e6ee3467de7630f4cc8db0a71a6f6dae07bbf0acafb68e8611bc2a87", "generation_seconds_batch": 14.745960708009079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8693875074386597, "target_z": 0.7617186859318559, "ce": 6.292664527893066, "genuineness": 4.256305694580078, "identity": 0.4425225853919983, "hypothesis": "The 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_Pleasure_Ecstasy/8ee27067a2a9dda9321b113f385919abf7cf057a5af5131f6883daafb7c44a28.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "8ee511b025e06651348973722ff0792f639fa81eb95aabb680725a394733a204", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e3505b4554edfa97a1f4ee00b2a602c870870e009c9d1e484c8d91532348c2ad", "generation_seconds_batch": 19.31928555702325, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0816422700881958, "target_z": 1.109375036610368, "ce": 6.24500846862793, "genuineness": 4.645420074462891, "identity": 0.6375554800033569, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8ee511b025e06651348973722ff0792f639fa81eb95aabb680725a394733a204.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": "8eeba9d5ef1a3dc9071c299a88b15eebf502327dce42ea8e70f08ed725d2b5c5", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d362d5f109954fa6cbcf53559eaee29458202ea39f76f62999282b8a730fa97", "generation_seconds_batch": 14.68258873198647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2247352600097656, "target_z": 1.3437499267792639, "ce": 6.1020402908325195, "genuineness": 4.281409740447998, "identity": 0.5917791724205017, "hypothesis": "De sleutels liggen op de keukentafel. Ik goede 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_Pleasure_Ecstasy/8eeba9d5ef1a3dc9071c299a88b15eebf502327dce42ea8e70f08ed725d2b5c5.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": "8f3962a722a4ce24f744d22e2c6db8bae9d2b48069d0046cfd953bd3f92a9e8d", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8aee4d22708bd822cb4edd16bbcc550c7a2eecab43757487d002c202b0ca17ce", "generation_seconds_batch": 20.515944015001878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.091181755065918, "target_z": 1.124999951186176, "ce": 6.252951145172119, "genuineness": 4.124508857727051, "identity": 0.5438989400863647, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego junto a la ventana llévatelas cuando te vayas.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8f3962a722a4ce24f744d22e2c6db8bae9d2b48069d0046cfd953bd3f92a9e8d.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "8f64cf28a70388064a1073c9f4531795ad0e437c7ea0526b67e6c7b82785212a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f02a183cdb190b833b7b83c8df65bbe22031b867c7b379eb564a83f9aab98d0a", "generation_seconds_batch": 19.69737080100458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9147003889083862, "target_z": 0.8359375671190081, "ce": 6.284721851348877, "genuineness": 3.911123275756836, "identity": 0.46693333983421326, "hypothesis": "The 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_Pleasure_Ecstasy/8f64cf28a70388064a1073c9f4531795ad0e437c7ea0526b67e6c7b82785212a.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "8fd1617b9d1055d05b4f93de0da59c5b4bb2cec9625d0f4ec5c676ae6fb2d680", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "eace65a1008e50edec17eba17e04ea38ef65a8c77d5ad86f69b904840edcd761", "generation_seconds_batch": 18.46147519396618, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7112517356872559, "target_z": 2.14062506101728, "ce": 6.09409761428833, "genuineness": 4.344170093536377, "identity": 0.343711256980896, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/8fd1617b9d1055d05b4f93de0da59c5b4bb2cec9625d0f4ec5c676ae6fb2d680.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "908bd861e26da281baaf24b6405ae03248b29701ddee2d2d145b69bf4a01c5a5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a564f7b85cfb281ac4a6e8fd5ff22d271eed4e4bb517c4f6975f8498df812017", "generation_seconds_batch": 22.705746703082696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8813120126724243, "target_z": 0.7812500732207361, "ce": 6.300607204437256, "genuineness": 4.319066047668457, "identity": 0.678442120552063, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/908bd861e26da281baaf24b6405ae03248b29701ddee2d2d145b69bf4a01c5a5.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "90a5cd44a090d2cce2f3e3ab22e062d6e6041a10bacadd51093abcd77df6890f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "998de0a6ad96edfc2d406f4b59a0cf7be62f8a00edaeb9c3b2232b934619b2f9", "generation_seconds_batch": 19.688823832082562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0816422700881958, "target_z": 1.109375036610368, "ce": 6.09409761428833, "genuineness": 3.747946262359619, "identity": 0.23736052215099335, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/90a5cd44a090d2cce2f3e3ab22e062d6e6041a10bacadd51093abcd77df6890f.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "90f4a1b344205a60d0cd8ab09196429d8aa761f502573421e8f302724bb481b7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b01b8ac981e4cccef2f790cd401c7e368f86ee9b1627e5cc292a6b0240e5e1fa", "generation_seconds_batch": 18.224183326936327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1214518547058105, "target_z": 2.812500097627648, "ce": 6.284721851348877, "genuineness": 4.231201171875, "identity": 0.5205685496330261, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/90f4a1b344205a60d0cd8ab09196429d8aa761f502573421e8f302724bb481b7.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "9186b04c924f716955dad1cb4b2842379bbb526cf79135407e5fe1a69e6ab9fe", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c04da8aa514b7cfd47473e030a1512432c31aa70f37c28c0f1c6f7cab80c647b", "generation_seconds_batch": 20.14059146598447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0387142896652222, "target_z": 1.0390624328809919, "ce": 6.483288764953613, "genuineness": 4.20609712600708, "identity": 0.4811553955078125, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie standen neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/9186b04c924f716955dad1cb4b2842379bbb526cf79135407e5fe1a69e6ab9fe.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "9242018b0a97b5194de47962a197db9b017bbc36ca1334024d4183f07a579dbe", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6def285eed17d110a4e61df751cb2909bc27617b9fc481d3948d700f56f35177", "generation_seconds_batch": 14.645402089925483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.596777319908142, "target_z": 1.9531251098311042, "ce": 6.252951145172119, "genuineness": 4.030367851257324, "identity": 0.6000868678092957, "hypothesis": "La porte 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_Pleasure_Ecstasy/9242018b0a97b5194de47962a197db9b017bbc36ca1334024d4183f07a579dbe.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "933898b2f8a81c3041e9990f31d7f6bcfc2beaa0b1b4798a857c7af3ee82d2dc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "6b1f1e4dc1e8c094af5684c4ce1c508d8635e5ab17babf59b973ad821acb2295", "generation_seconds_batch": 21.54415443202015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6273217797279358, "target_z": 0.36523435516938396, "ce": 6.372091293334961, "genuineness": 4.293961524963379, "identity": 0.30472680926322937, "hypothesis": "The 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_Pleasure_Ecstasy/933898b2f8a81c3041e9990f31d7f6bcfc2beaa0b1b4798a857c7af3ee82d2dc.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "93a97c415ce096ac5ad051474b193091909a20a428d4b810dfe7b9f6547e856a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8a07eecea6f8bcd2585b3ddce9e496ae404f0b579338635574854618cf60dc00", "generation_seconds_batch": 22.592707652016543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4770740866661072, "target_z": 0.11914063262716001, "ce": 6.197352409362793, "genuineness": 4.243753433227539, "identity": 0.6758430004119873, "hypothesis": "De deur 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_Pleasure_Ecstasy/93a97c415ce096ac5ad051474b193091909a20a428d4b810dfe7b9f6547e856a.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "93dc3444dd2ce729372019724f5cabcc0d7b6c4e8d8dd8e94d28f5b2e274b39d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "2bb82aa4f8bcb5ff166297c2033c2d2165c86b65a7425051972aa4a3e72a4287", "generation_seconds_batch": 19.69737080100458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.091181755065918, "target_z": 1.124999951186176, "ce": 6.0146708488464355, "genuineness": 3.8797430992126465, "identity": 0.43326133489608765, "hypothesis": "The 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_Pleasure_Ecstasy/93dc3444dd2ce729372019724f5cabcc0d7b6c4e8d8dd8e94d28f5b2e274b39d.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "94094968598ae424a6a7220641d74952b7d968b01c54a01c255e376536581c5a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "271ccfa6aa677ef1107a68c3bcf472517adcf7fb821c09fb95b2c388b0b1a819", "generation_seconds_batch": 19.618075890932232, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5300005674362183, "target_z": 1.8437501220345602, "ce": 6.149696350097656, "genuineness": 3.961331605911255, "identity": 0.4686036705970764, "hypothesis": "The 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_Pleasure_Ecstasy/94094968598ae424a6a7220641d74952b7d968b01c54a01c255e376536581c5a.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "941d7d4ac04226e9a98a37f4037d229a5d2fa50f2a68fc6486694d11dae5a73a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c9ee297d239112a64845121efe1fd68452b751e5b02e94f41f4f3db0111d7e88", "generation_seconds_batch": 20.699490900035016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9790922403335571, "target_z": 0.941406277457776, "ce": 6.300607204437256, "genuineness": 4.469690799713135, "identity": 0.6953785419464111, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/941d7d4ac04226e9a98a37f4037d229a5d2fa50f2a68fc6486694d11dae5a73a.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "942111b65b269012d985caf310e9bb2741828a532f994aaf95d415536976dbd7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "09312a7a2629f4cd96cd517a4ee1104bf6637c4d2076840e424db32a67fbcc76", "generation_seconds_batch": 17.545284545980394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.159609794616699, "target_z": 2.8749997559308795, "ce": 6.054384231567383, "genuineness": 3.7040140628814697, "identity": 0.5640166997909546, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/942111b65b269012d985caf310e9bb2741828a532f994aaf95d415536976dbd7.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "9428fcc071f743cea16ab2fb6eb32e58f6c453d013059fe98e011dc91b89ad1a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "88b129f6c2f6396b7376fd81a57476d9af57ef0c3523632a3fa61763fa440ba5", "generation_seconds_batch": 21.12001184502151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.401216745376587, "target_z": 1.632812506101728, "ce": 5.990842819213867, "genuineness": 3.9173994064331055, "identity": 0.41697239875793457, "hypothesis": "The 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_Pleasure_Ecstasy/9428fcc071f743cea16ab2fb6eb32e58f6c453d013059fe98e011dc91b89ad1a.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": "955ebfa46e929153a0b861eb8a72ce728222a054b28d81285dd5aef979789979", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "bdb4465bdefdb304e9f382f788d81537b9fa6601eefd219affd1ff5b90e3567f", "generation_seconds_batch": 24.45478479808662, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33517345786094666, "target_z": -0.11328126525432003, "ce": 6.157639026641846, "genuineness": 4.532451152801514, "identity": 0.7107530832290649, "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_Pleasure_Ecstasy/955ebfa46e929153a0b861eb8a72ce728222a054b28d81285dd5aef979789979.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "958e487bc76d9d7d8b048b2cce2b33471f2d12bf3f42b5fac50f89a23386a77a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "009e51c61f093d4024af2d8952ef003166948ab4545f27c7f35047f0ffab079d", "generation_seconds_batch": 19.75718708895147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8925029039382935, "target_z": 2.4375, "ce": 6.252951145172119, "genuineness": 4.13078498840332, "identity": 0.6261547207832336, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/958e487bc76d9d7d8b048b2cce2b33471f2d12bf3f42b5fac50f89a23386a77a.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "95a87ebf38c3997afa6f9fc4693c2761022194e8bd5e86c96da5cd7bea1eeb9f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "65539a31d1949b811f490b7238fa3a228a5e2b516cb789dac52eaf3629b2773f", "generation_seconds_batch": 15.722736891009845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8574631214141846, "target_z": 0.742187493898272, "ce": 6.507116317749023, "genuineness": 4.13078498840332, "identity": 0.4143229126930237, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/95a87ebf38c3997afa6f9fc4693c2761022194e8bd5e86c96da5cd7bea1eeb9f.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "95f03bb120b2da70b7ca48c99e9ce2b59bfd20fcfa27e344263333f98f51ff6f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a6fac184957f37316089f8334b4a2d600816d6f44ad7f970f8844302efe0e836", "generation_seconds_batch": 15.722736891009845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0196352005004883, "target_z": 1.0078124084740798, "ce": 6.403861999511719, "genuineness": 4.319066047668457, "identity": 0.5645098686218262, "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_Pleasure_Ecstasy/95f03bb120b2da70b7ca48c99e9ce2b59bfd20fcfa27e344263333f98f51ff6f.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "965beb8994f9c803b44c9dcbb9adfe3864be04b6d3eb6f4b55b110f4fe036a3b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b34bfb6a75d9f6fb426e5f3605b59c89a2bf8339008d9bba582640f359171547", "generation_seconds_batch": 20.022982187918387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6535555124282837, "target_z": 0.408203114321976, "ce": 5.990842819213867, "genuineness": 4.017816066741943, "identity": 0.20275849103927612, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/965beb8994f9c803b44c9dcbb9adfe3864be04b6d3eb6f4b55b110f4fe036a3b.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "96ddb63f4e25577ac27aa760cf1c08833d29d911fb39aa6ddf075b3a2c7cc8e0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "498071064587cea1474e328ba152ee364bebf8ae5a686e5a370ae4eded35377c", "generation_seconds_batch": 17.507333416957408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5170208811759949, "target_z": 0.18457029190666796, "ce": 6.038498878479004, "genuineness": 4.300237655639648, "identity": 0.44550490379333496, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/96ddb63f4e25577ac27aa760cf1c08833d29d911fb39aa6ddf075b3a2c7cc8e0.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": "96e25ac61541079ab95ea24aaf4580aeed4854b1b24a87e7a92e8df58945dcc0", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0977d918372256d4d7b964648ab9630b4511b6fbb47086fdb4976379b32db74", "generation_seconds_batch": 14.68258873198647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4679934978485107, "target_z": 1.742187493898272, "ce": 6.324435234069824, "genuineness": 4.337893962860107, "identity": 0.13077780604362488, "hypothesis": "Sleutels lig op de keukentafel. Ik keek 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_Pleasure_Ecstasy/96e25ac61541079ab95ea24aaf4580aeed4854b1b24a87e7a92e8df58945dcc0.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "96f13999386bec3fc50e81dd345116005b132e3ca04c466d2183f275eaee4429", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b006bdb86fbed0917c2d301544d8fe84662b707318bfcd38221d8850623b19eb", "generation_seconds_batch": 22.592707652016543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37839949131011963, "target_z": -0.04248047447037001, "ce": 6.09409761428833, "genuineness": 4.369274139404297, "identity": 0.6597696542739868, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/96f13999386bec3fc50e81dd345116005b132e3ca04c466d2183f275eaee4429.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "96f56ba9a2dd64b074936eaf48cf27766663b4c203f46c3ae884418f14f85530", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "7ef91d6ffd35e40dbb59e56b963354e429f4ff51099acb23a5e85140c4b8df67", "generation_seconds_batch": 17.71004897810053, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2819725275039673, "target_z": 1.4375, "ce": 5.879645347595215, "genuineness": 3.936227321624756, "identity": 0.3393940031528473, "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_Pleasure_Ecstasy/96f56ba9a2dd64b074936eaf48cf27766663b4c203f46c3ae884418f14f85530.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "96fae3f3bf515d0f0b89cb1038889f494938ffa292e91715e118db42cfc7ffec", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3e6a43781abc9615e2fad3083db648c7b855ec40712a8b83c3aec8b5591a3eb0", "generation_seconds_batch": 15.614952877047472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5414659380912781, "target_z": 0.22460934296592794, "ce": 6.181467056274414, "genuineness": 4.356721878051758, "identity": 0.31769198179244995, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/96fae3f3bf515d0f0b89cb1038889f494938ffa292e91715e118db42cfc7ffec.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "97110dbca5620806f5fcac8546c1b6f70847542716d4066d8602b094c9ef8fb9", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8b6d99a9a7a81c69a2485c84ea65b60cd8190d04945047f1839a8770eceb30f6", "generation_seconds_batch": 21.4190079360269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26899293065071106, "target_z": -0.22167968368642, "ce": 6.23706579208374, "genuineness": 4.394378662109375, "identity": 0.5981694459915161, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/97110dbca5620806f5fcac8546c1b6f70847542716d4066d8602b094c9ef8fb9.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "973bedddbfb427fa6a401ad89e0e3d51bcbaedc56a189e0d9ace8a098686d5bf", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0b5fdbffabd88e1d4ceadd0429fd9d856d734e65bd12ab52290fd9a1a18b7e2f", "generation_seconds_batch": 15.643510648980737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8734238147735596, "target_z": 2.406249975593088, "ce": 6.284721851348877, "genuineness": 3.9927117824554443, "identity": 0.5364891290664673, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/973bedddbfb427fa6a401ad89e0e3d51bcbaedc56a189e0d9ace8a098686d5bf.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": "975b0cac78184fb19a11a5b101016091c0e046cae107060841c771e1b4512ceb", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4dc52050d7cffb137d7229dce9e55020e82455558278f99ed8093490b2098de7", "generation_seconds_batch": 15.995910958037712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.558160126209259, "target_z": 0.25195308991506393, "ce": 6.38003396987915, "genuineness": 4.2249250411987305, "identity": 0.5967077016830444, "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_Pleasure_Ecstasy/975b0cac78184fb19a11a5b101016091c0e046cae107060841c771e1b4512ceb.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "976f853396160bb09ab4839eecb53064e37aa6c31cbb0492e189acf97adf4fec", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "4f87a03398c70aba9112b99bddb6ee56befca0c9cf942f78d2da3c0cdea89281", "generation_seconds_batch": 20.333195818937384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3755674362182617, "target_z": -0.04711915454456702, "ce": 6.316492557525635, "genuineness": 4.18099308013916, "identity": 0.3996538519859314, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/976f853396160bb09ab4839eecb53064e37aa6c31cbb0492e189acf97adf4fec.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "97c58e384015c74ac1b3bc1d355a009cb1499da1874e85f775686ce6c2e9851f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "adebe3cef8c3ddde4fdf8e06c7dcd59e176dab4c77c153401b22791ffc5f2b6f", "generation_seconds_batch": 20.13814310694579, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5194057822227478, "target_z": 0.188476569364444, "ce": 6.459460258483887, "genuineness": 4.030367851257324, "identity": 0.4441642463207245, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/97c58e384015c74ac1b3bc1d355a009cb1499da1874e85f775686ce6c2e9851f.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": "984f4c23943bd10680c3b17c522c95d480cc2c5a4c08c8d158a2b49a76d62afb", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ed90e5ab1a58b2420cd210352b6e4f6b800be99fdc36be7ace3463160aba56a", "generation_seconds_batch": 17.788708267034963, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9480887651443481, "target_z": 0.8906250610172801, "ce": 6.268836498260498, "genuineness": 4.256305694580078, "identity": 0.669367790222168, "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_Pleasure_Ecstasy/984f4c23943bd10680c3b17c522c95d480cc2c5a4c08c8d158a2b49a76d62afb.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "987fe9b65b18de6bda25c64d7f7d4610fee2987f62149a8305d1418829c67894", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "6fb1b4582a4363d2f258b16dc9e1c4149af75deedfbbf41a19cd6ea836bc61e3", "generation_seconds_batch": 20.311819492955692, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4615723490715027, "target_z": 0.09375002440691203, "ce": 6.252951145172119, "genuineness": 4.331617832183838, "identity": 0.5075556039810181, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/987fe9b65b18de6bda25c64d7f7d4610fee2987f62149a8305d1418829c67894.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "ca4b0db3664aacfb211f79e7357783710a00955b656dd94893c5ae651bd7f0bd", "generation_seconds_batch": 15.879963418934494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19565773010253906, "target_z": -0.341796885678024, "ce": 6.546830177307129, "genuineness": 4.808597087860107, "identity": 0.38415616750717163, "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_Pleasure_Ecstasy/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "99debc6ab7c0982418eff91f933181aa10535c3e4e3ce2cb984cd6e91934bafb", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0687beafacdff5b8728c8aec1104ba3b8d04f15e194b580618b4811f6de657d7", "generation_seconds_batch": 15.643510648980737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6349353790283203, "target_z": 2.015624963389632, "ce": 6.372091293334961, "genuineness": 4.256305694580078, "identity": 0.5905627012252808, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/99debc6ab7c0982418eff91f933181aa10535c3e4e3ce2cb984cd6e91934bafb.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": "9a0d974f8b849f04e3b963650d57c818577bedf714d267625bc1fc6a5a2b0728", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca8b9a31edcdeda3292730bb01ee85866ee14653d246684a29610135393734e9", "generation_seconds_batch": 17.48583423101809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0387142896652222, "target_z": 1.0390624328809919, "ce": 6.356205940246582, "genuineness": 4.607763767242432, "identity": 0.8190216422080994, "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_Pleasure_Ecstasy/9a0d974f8b849f04e3b963650d57c818577bedf714d267625bc1fc6a5a2b0728.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "9a4c2c5a957b4a2b0eadfcbc651f1b735f6b858757a5cabe75b431854a6c3597", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f0f1903b1cbe0be0b3d311b364fc827d91c2bb86ce05752831c6df4926260950", "generation_seconds_batch": 20.97253055893816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.320130705833435, "target_z": 1.500000048813824, "ce": 6.205295085906982, "genuineness": 4.325342178344727, "identity": 0.4560514986515045, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/9a4c2c5a957b4a2b0eadfcbc651f1b735f6b858757a5cabe75b431854a6c3597.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "9a66eac1df42d97e40251f876a94d87ca775a579ebfcf8712f72e1d1ccd6a83e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "23e88f5c7f77dc3d8c5ff0628219b6c0623fa5a003715c9e0629f497b1ed2a73", "generation_seconds_batch": 17.92179599800147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20281238853931427, "target_z": -0.330078126525432, "ce": 6.141753673553467, "genuineness": 4.375550270080566, "identity": 0.7756133079528809, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/9a66eac1df42d97e40251f876a94d87ca775a579ebfcf8712f72e1d1ccd6a83e.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": "9a854d2bf38137b020423a3e39e23d477d02ffa37b2a39a935f2a9b0883bd8e4", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "720907b95a7d116be4ae5532d907951bc37c2c5545124dfd7c460ecc5ca0ad9e", "generation_seconds_batch": 15.221329036052339, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3153609037399292, "target_z": 1.492187493898272, "ce": 6.1894097328186035, "genuineness": 4.3127899169921875, "identity": 0.34461426734924316, "hypothesis": "Deine Nachricht kam, als sie schon weg war. Ich las sie zweimal, dann legte ich das Handy weg. Sag mir, wann wir reden können.", "wer": 0.041666666666666664, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/9a854d2bf38137b020423a3e39e23d477d02ffa37b2a39a935f2a9b0883bd8e4.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": "9a867f3fd17e6e15d981693866bb4258e79035f8f0c7dd14abcde05b91f41138", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "91af2f91631b389869e5a028a9e28c44856df77ddc0665cd6b953c040dd2b52e", "generation_seconds_batch": 15.435156753985211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7906863689422607, "target_z": 0.632812506101728, "ce": 5.927301406860352, "genuineness": 4.362998008728027, "identity": 0.7053903341293335, "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_Pleasure_Ecstasy/9a867f3fd17e6e15d981693866bb4258e79035f8f0c7dd14abcde05b91f41138.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "9adb89538d1cb04bd206056f0a041260b068d70b55962a7f322b4969e4984c5e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d2802d6d1e0510450ca012735473cbaf45fa0e628bdde94b868e265e43630be5", "generation_seconds_batch": 24.551556656952016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2199655771255493, "target_z": 1.3359375671190081, "ce": 6.09409761428833, "genuineness": 4.425758361816406, "identity": 0.7130820751190186, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/9adb89538d1cb04bd206056f0a041260b068d70b55962a7f322b4969e4984c5e.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": "9b0afae8a24e0469a97ae400247e6e9da98c31df9752f000e5bf9373e7f1f9f3", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7fb2fc61e07d5512bab42edaad7b30c93afa69cc8bf6eedbf961fa5b6ff38430", "generation_seconds_batch": 16.13663615495898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8097654581069946, "target_z": 0.6640625305086401, "ce": 6.435632705688477, "genuineness": 4.319066047668457, "identity": 0.529293417930603, "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_Pleasure_Ecstasy/9b0afae8a24e0469a97ae400247e6e9da98c31df9752f000e5bf9373e7f1f9f3.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": "9b8d88cf61ba1e8d67001dd99b9aef80843b7e08aae0b9f76f44ca2a69e2d4bf", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f7cdfb05493624c8915064ffd59634ef0dd408d3bab8de84d264ce25af3d4ea5", "generation_seconds_batch": 16.048848994076252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.560545027256012, "target_z": 0.25585936737284, "ce": 6.340320587158203, "genuineness": 4.287685871124268, "identity": 0.6550043821334839, "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_Pleasure_Ecstasy/9b8d88cf61ba1e8d67001dd99b9aef80843b7e08aae0b9f76f44ca2a69e2d4bf.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "9bcfce38d003bfec4b45cbf37b00d4fab70c7604ae90c81d272cd506cee17e8a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "23d5a8cacc92f688d8274d29facebe2d88eaa097a5cd2cdd4edfe77567c6fffb", "generation_seconds_batch": 22.579436086001806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7000607252120972, "target_z": 0.4843749389827199, "ce": 6.538887023925781, "genuineness": 3.9550557136535645, "identity": 0.5023478865623474, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/9bcfce38d003bfec4b45cbf37b00d4fab70c7604ae90c81d272cd506cee17e8a.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "c97fa55b8d4a31f4504c83ecc37ebc492c604cfa8b740cffe2bec87a736e62c7", "generation_seconds_batch": 17.54697629401926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04183271527290344, "target_z": -0.593749975593088, "ce": 6.1894097328186035, "genuineness": 4.394378662109375, "identity": 0.8379771113395691, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Stond hier naast de hoge boekenkast. We zetten het na 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_Pleasure_Ecstasy/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "9c5788d891c63973f9c4ce9ac543c95141f613d6960de79eecf096d0bdc2bc55", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f5c6cd3429a07c9c98929a4253f8db6869c45bd2c96454249b35d236843ead14", "generation_seconds_batch": 20.357400125009008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6213595867156982, "target_z": 0.355468759152592, "ce": 6.41180419921875, "genuineness": 4.111956596374512, "identity": 0.4585004150867462, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/9c5788d891c63973f9c4ce9ac543c95141f613d6960de79eecf096d0bdc2bc55.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "9c6a7ebdd75cc5214ca4196c174248667b9ffe8704b05de9b413250355e2a614", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "360f1f185f420f2b6f61277c0a6e412deb773af167d107db2c097c153571db4c", "generation_seconds_batch": 14.529642662033439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8622329235076904, "target_z": 0.7500000488138241, "ce": 6.475345611572266, "genuineness": 4.124508857727051, "identity": 0.43605124950408936, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/9c6a7ebdd75cc5214ca4196c174248667b9ffe8704b05de9b413250355e2a614.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "8a44149a7df37f2df84fd91157420f5e072e2a1eb39c0f5c15c749711e9f15d6", "generation_seconds_batch": 15.142867924994789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10264724493026733, "target_z": -0.49414063262716, "ce": 6.141753673553467, "genuineness": 4.532451152801514, "identity": 0.8195067644119263, "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_Pleasure_Ecstasy/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "9cb82ccf2c02f5a9c52f995de1e1dfbf913739115b5f39be43b7b8c47090d178", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3d086da4d7ecd164eebbb4359478d2cfa848b9ad79248c509816aac836b796d8", "generation_seconds_batch": 17.41127325000707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9020425081253052, "target_z": 2.453125109831104, "ce": 6.125868320465088, "genuineness": 4.2374773025512695, "identity": 0.6150957345962524, "hypothesis": "La porte 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_Pleasure_Ecstasy/9cb82ccf2c02f5a9c52f995de1e1dfbf913739115b5f39be43b7b8c47090d178.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "9d856c290cdf4fc37f9e58a5f2da1592c13b147d58539d0ce708657ea79e6e28", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0db1bb4c7e8b5f0ab517e44124d8dccdf32a44a4ffe8dd0e10f3155ee907ae1a", "generation_seconds_batch": 20.802036282024346, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7883014678955078, "target_z": 0.628906228643952, "ce": 6.252951145172119, "genuineness": 4.507347106933594, "identity": 0.6145961880683899, "hypothesis": "La porte 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_Pleasure_Ecstasy/9d856c290cdf4fc37f9e58a5f2da1592c13b147d58539d0ce708657ea79e6e28.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": "9da88cf949e171759b44f26fe464b4c7ce9d2a9a8f70e217e1bcba955a330613", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d3c293505de6fc47e6e17116affc8913d840da7e1ef79401329125d01e768984", "generation_seconds_batch": 20.752569730044343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49257582426071167, "target_z": 0.14453124084740798, "ce": 6.1020402908325195, "genuineness": 4.300237655639648, "identity": 0.5287374258041382, "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_Pleasure_Ecstasy/9da88cf949e171759b44f26fe464b4c7ce9d2a9a8f70e217e1bcba955a330613.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "9dcb533151304ab4ec30527f3bbf498fcbad8f58a15c0dddfbeaac89efccef36", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "841dd5122d2335f63cac79c304edbbaf8c36bbd55842773e8d9dfd3acb43edde", "generation_seconds_batch": 21.54415443202015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3775051534175873, "target_z": -0.043945328517036024, "ce": 6.268836498260498, "genuineness": 4.2374773025512695, "identity": 0.39479804039001465, "hypothesis": "The 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_Pleasure_Ecstasy/9dcb533151304ab4ec30527f3bbf498fcbad8f58a15c0dddfbeaac89efccef36.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": "9e886099af051011cfb330055e1a3edf925395865c2e2368243c1d66409a5fef", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e6dc10a13c645d646b041075d5fb4d63ab1e6ac34880f801e53830c35d3ec965", "generation_seconds_batch": 20.579113692045212, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.05614200234413147, "target_z": -0.570312506101728, "ce": 6.0305562019348145, "genuineness": 4.2751336097717285, "identity": 0.6367179155349731, "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_Pleasure_Ecstasy/9e886099af051011cfb330055e1a3edf925395865c2e2368243c1d66409a5fef.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "9ee86db2e913d535084ff0bb9e5c992677ed764f804084fb2d6e8b6478c1cff3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f23c1a48bda52b32eaf142b121f7455e32b344da6fa161ce7679c71069dc51a8", "generation_seconds_batch": 19.48322176700458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6785967946052551, "target_z": 0.44921873474567997, "ce": 6.141753673553467, "genuineness": 4.362998008728027, "identity": 0.35822099447250366, "hypothesis": "De deur 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_Pleasure_Ecstasy/9ee86db2e913d535084ff0bb9e5c992677ed764f804084fb2d6e8b6478c1cff3.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "9efb9253801c3bd003259b6a64508a91b901e3e83e8af7611df8cb9c63ce10c4", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "633fa9ac9d1dca5cef2464f5a572c17ab478488433b80ffec82ff6a67d9f48fb", "generation_seconds_batch": 21.063327872077934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.615856409072876, "target_z": 1.9843751342380163, "ce": 6.348263263702393, "genuineness": 4.193545341491699, "identity": 0.33482056856155396, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/9efb9253801c3bd003259b6a64508a91b901e3e83e8af7611df8cb9c63ce10c4.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": "9f1bc46603b8afecd0b9c5e8e8425df4b052d497cbcb19df5d9a4b9e379909dc", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a6f668037750a6a77edc87c64f711efeb7d642a1ed6bd6e23faee1c996e8a6b9", "generation_seconds_batch": 24.316788019961677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9003910422325134, "target_z": 0.8125, "ce": 6.483288764953613, "genuineness": 4.557555198669434, "identity": 0.5559700727462769, "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_Pleasure_Ecstasy/9f1bc46603b8afecd0b9c5e8e8425df4b052d497cbcb19df5d9a4b9e379909dc.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": "9f5c88d5a6a0dec874f317431617e7b5ce52a12f54bd67496bd74b42cea07881", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a8d893b266e261479a1d0b90cf5ae02980020831baaadc59360ef0bc59e2a29c", "generation_seconds_batch": 19.558017925941385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2962818145751953, "target_z": 1.46093746949136, "ce": 6.316492557525635, "genuineness": 4.250029563903809, "identity": 0.6408672332763672, "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_Pleasure_Ecstasy/9f5c88d5a6a0dec874f317431617e7b5ce52a12f54bd67496bd74b42cea07881.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": "9fd3e5693b16e41c76cbead7dd1ab4a69aacd70820f9c98e48a058b016643c0b", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e326055c749064dea96d098c76aa01cc3120388b1b9d512709d7dd8477562354", "generation_seconds_batch": 17.144625050015748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8574631214141846, "target_z": 0.742187493898272, "ce": 6.078212261199951, "genuineness": 4.6705241203308105, "identity": 0.7326803803443909, "hypothesis": "J'ai écrit le numéro sur l'enveloppe. Lis-lu bien et vérifie les deux derniers chiffres. Appelle-moi quand tu auras un moment.", "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_Pleasure_Ecstasy/9fd3e5693b16e41c76cbead7dd1ab4a69aacd70820f9c98e48a058b016643c0b.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": "a11c4671cedf3a3a85ffba624d75e7fc98b74ad04ce6f73b785a3a9b1c0450a2", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "27896036161bc7e78107c866f7359257c4c2d04cf752c26f16d4ea998183ea69", "generation_seconds_batch": 16.12436462601181, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2994002103805542, "target_z": -0.17187498779654398, "ce": 6.515059471130371, "genuineness": 4.519899368286133, "identity": 0.4455336332321167, "hypothesis": "Jemand hat den kleinen blauen Stuhl umgestellt. Er stand hier, neben dem Hohnbücherregal. Wir stellen ihn nach dem Essen zurück.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a11c4671cedf3a3a85ffba624d75e7fc98b74ad04ce6f73b785a3a9b1c0450a2.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "a151483effb76b3301845500cfaf5724b2501ab5b32bdaf118a37d800658893b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "89dc233dcd2a31db026f5900b93dfec587e88a5d3e3fc3ebf061c62ae3aac49c", "generation_seconds_batch": 14.68925620103255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1913468837738037, "target_z": 1.2890624328809919, "ce": 6.197352409362793, "genuineness": 4.030367851257324, "identity": 0.0944863110780716, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a151483effb76b3301845500cfaf5724b2501ab5b32bdaf118a37d800658893b.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "a1b11b3f81b3e76cc2d32692318f1b051af3c7c1057176fafb46a0c7f1c14d00", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a7898dab5cffe696aa66fa69b1b23f4083850fedae6f11285dbfbf067efa4ef8", "generation_seconds_batch": 19.68717737402767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6750195026397705, "target_z": 0.4433594161866641, "ce": 5.974957466125488, "genuineness": 4.055472373962402, "identity": 0.274505615234375, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a1b11b3f81b3e76cc2d32692318f1b051af3c7c1057176fafb46a0c7f1c14d00.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "a1b6282d8fdc661264275709d0175e2d726756ccaa164ea3698a0ed61fd1898c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ae7b80d78da437cd9d8b2896216afbd760d508cb28ca8e27190a006d76cd98a3", "generation_seconds_batch": 20.29940816690214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6177822351455688, "target_z": 0.34960934296592794, "ce": 6.221180438995361, "genuineness": 4.306513786315918, "identity": 0.11042015254497528, "hypothesis": "De dieren staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a1b6282d8fdc661264275709d0175e2d726756ccaa164ea3698a0ed61fd1898c.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "a1ce0d313724887deec290c6cc1119a1a4b7eac5e48935077b8a8fa4d5b545b5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "98316628e810511f90e667e1148b10e1da8e0ee2b3c208e8f637b6773b32cc93", "generation_seconds_batch": 19.42391296196729, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4870725870132446, "target_z": 1.773437518305184, "ce": 6.022613525390625, "genuineness": 4.381826400756836, "identity": 0.03102133795619011, "hypothesis": "De deur 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_Pleasure_Ecstasy/a1ce0d313724887deec290c6cc1119a1a4b7eac5e48935077b8a8fa4d5b545b5.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "a1f37c485a4fc22d9903bf1571eca5e2c56951383bea18f21641ab409b9ebea7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "721ebb1fa17d56c0a982e7ea1ebd88804840d6f3e22d5b78fba3df9fde0b2bdf", "generation_seconds_batch": 18.224183326936327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0832936763763428, "target_z": 2.750000048813824, "ce": 6.197352409362793, "genuineness": 4.319066047668457, "identity": 0.5898219347000122, "hypothesis": "J'ai trouvé la petite boîte! Elle était boite, elle était près de la vieille fenêtre. We've regarded ensemble what contien?", "wer": 0.47368421052631576, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a1f37c485a4fc22d9903bf1571eca5e2c56951383bea18f21641ab409b9ebea7.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "a23a221aee5f9e027d5b5464a5c60e9603cee4bf3b02bcf1fded1fad00f3ced5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "9e98b9b86b31359b8edc88ddd3dcdd3a71c1ad2388fd71d3197cd64eb2a80616", "generation_seconds_batch": 20.29940816690214, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.766837477684021, "target_z": 0.5937499267792639, "ce": 6.133810997009277, "genuineness": 4.406930446624756, "identity": 0.06679937988519669, "hypothesis": "De deur er staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a23a221aee5f9e027d5b5464a5c60e9603cee4bf3b02bcf1fded1fad00f3ced5.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "a27881b4594ca4633d51e96bb332a8aeaea2c5e744a146e896d5df49e77541ed", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "465a51c59d5c09ea2674fb2a367b5f16d5c30177627815f2b0f471f835d9a60b", "generation_seconds_batch": 20.56486617901828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.057793378829956, "target_z": 1.070312457287904, "ce": 6.213237762451172, "genuineness": 4.519899368286133, "identity": 0.646612286567688, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a27881b4594ca4633d51e96bb332a8aeaea2c5e744a146e896d5df49e77541ed.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "a2a105e08e9efc555c2e935db0e4aa7af87a2aa90f7fb4c84636c58c87d9a6e8", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "02c65867c7e0acdbf77515747516580d800b67481c24441f8cb16e683c68cb11", "generation_seconds_batch": 21.24071636691224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6475933194160461, "target_z": 0.39843751830518404, "ce": 6.149696350097656, "genuineness": 3.936227321624756, "identity": 0.32081544399261475, "hypothesis": "The 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_Pleasure_Ecstasy/a2a105e08e9efc555c2e935db0e4aa7af87a2aa90f7fb4c84636c58c87d9a6e8.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "a2a7f67941a5bc25ffb90bc7ebd827fa0cdf914d96b0b16821de0ff3fe9c3e0b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "5717f117ccff8ae3e49e7a1d27f3bd105b958eabc81f0dfba3f5e9ec1498b7d6", "generation_seconds_batch": 20.270910598919727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5736619234085083, "target_z": 0.2773437957629601, "ce": 6.252951145172119, "genuineness": 4.111956596374512, "identity": 0.27581703662872314, "hypothesis": "The 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_Pleasure_Ecstasy/a2a7f67941a5bc25ffb90bc7ebd827fa0cdf914d96b0b16821de0ff3fe9c3e0b.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": "a33d0a9d5b12c167553de7ecce7571c80e3de4f90846f1ea73cd303c5259dbbd", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4bfc0f768d91d0bf371ee1253c73ff7c5c15ea41345dd3615694074d1f704847", "generation_seconds_batch": 23.10895527305547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9147003889083862, "target_z": 0.8359375671190081, "ce": 6.157639026641846, "genuineness": 4.356721878051758, "identity": 0.6316729187965393, "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_Pleasure_Ecstasy/a33d0a9d5b12c167553de7ecce7571c80e3de4f90846f1ea73cd303c5259dbbd.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "a36beae5e1cb14a2e46f2b120e8d21cf685f0ff169211df4c7fd795fe5c0abd1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a3f39e59da2928f8d4d8a8b7df81938762c183d99a0d4eb775ab7d4b002ebf4e", "generation_seconds_batch": 20.380356651963666, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24931763112545013, "target_z": -0.253906253050864, "ce": 6.300607204437256, "genuineness": 4.143336772918701, "identity": 0.34861165285110474, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a36beae5e1cb14a2e46f2b120e8d21cf685f0ff169211df4c7fd795fe5c0abd1.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "a399cad62ed130671128d23fc2d5072fbdd2556c69648f67a396293710dff32e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d4499d907022c8cc6d4a39b055fe493ec117264bfef5c1ad6314994816cd9c22", "generation_seconds_batch": 20.667333946097642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9020425081253052, "target_z": 2.453125109831104, "ce": 6.173524379730225, "genuineness": 4.262581825256348, "identity": 0.46197831630706787, "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_Pleasure_Ecstasy/a399cad62ed130671128d23fc2d5072fbdd2556c69648f67a396293710dff32e.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": "a3f4199025a9f47444ebeeafe7a4c45ebc86548e9b78a29f1e5beb5200be7cfe", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "64bc609ba0a23b5dbeeb603eca715f1b9dd98c62568a85b6d0b67cd8f80fba13", "generation_seconds_batch": 22.763662477955222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2008864879608154, "target_z": 1.304687542712096, "ce": 6.268836498260498, "genuineness": 4.419482707977295, "identity": 0.6725808382034302, "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_Pleasure_Ecstasy/a3f4199025a9f47444ebeeafe7a4c45ebc86548e9b78a29f1e5beb5200be7cfe.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "a3f4be2875a64a1fe205f18fe95ae4b61c9fad924720ae12e610db9402cd5a95", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3e3f6739e27a8981f9f982a936baffadbf5c529bb5e406af60d97ac275d9bbd0", "generation_seconds_batch": 20.289955877000466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4202958345413208, "target_z": 1.66406253050864, "ce": 6.165581703186035, "genuineness": 4.369274139404297, "identity": 0.6000190377235413, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a3f4be2875a64a1fe205f18fe95ae4b61c9fad924720ae12e610db9402cd5a95.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "a43185b94ef69a9d6689fddc817e40bebbfaa60868769fad80c586f1df81ff65", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4bc7cdbab12310a7c201b21ed493ff20347f87eb73a83edb17b0332083318142", "generation_seconds_batch": 20.325607487000525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8598480224609375, "target_z": 0.746093771356048, "ce": 5.927301406860352, "genuineness": 4.300237655639648, "identity": 0.5556798577308655, "hypothesis": "La porte 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_Pleasure_Ecstasy/a43185b94ef69a9d6689fddc817e40bebbfaa60868769fad80c586f1df81ff65.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "a4a0f77da7ad1f9bb2eb27dd14a287a4c67ccdd5be11142b8c619322c5e3442e", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "980f2aee43e67a783b5b1c010837895e0afedd590cc100347cfe27a420872596", "generation_seconds_batch": 16.717534753028303, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3101321756839752, "target_z": -0.15429688567802402, "ce": 6.308549880981445, "genuineness": 4.720732688903809, "identity": 0.5204825401306152, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a4a0f77da7ad1f9bb2eb27dd14a287a4c67ccdd5be11142b8c619322c5e3442e.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "a5741524229fd20f466f557f35336e90ba587bccadb412fa89fe163984edb4a8", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6decb701b79aed2c09923ba4c77e7204d73dd7a52d8280f5ba1357670fd6ba58", "generation_seconds_batch": 15.515536317019723, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4776703119277954, "target_z": 0.12011720199160403, "ce": 6.078212261199951, "genuineness": 4.143336772918701, "identity": 0.39331382513046265, "hypothesis": "De deur 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_Pleasure_Ecstasy/a5741524229fd20f466f557f35336e90ba587bccadb412fa89fe163984edb4a8.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "a68ac1ee2119cf5a9559555abb3a059945cf0329c565c4be8a157affb33cccf7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "076095e4fb5e9d49da2d71b18959f59201dbc9be601b41d9757e2d1f4bd56133", "generation_seconds_batch": 21.208136413013563, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.673093557357788, "target_z": 2.078125012203456, "ce": 5.5659098625183105, "genuineness": 3.7542223930358887, "identity": 0.5840924382209778, "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_Pleasure_Ecstasy/a68ac1ee2119cf5a9559555abb3a059945cf0329c565c4be8a157affb33cccf7.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "a6a68d331f7cfeac33071db877692f49e891f054658e479c50a6f4b382176a6c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d97a88aead31cefc26d6d12d8201e1a80890780ce76160fdf0e21f8b0dc3dc56", "generation_seconds_batch": 15.511275833006948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2628934383392334, "target_z": 1.406249975593088, "ce": 6.24500846862793, "genuineness": 4.607763767242432, "identity": 0.6862484812736511, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a6a68d331f7cfeac33071db877692f49e891f054658e479c50a6f4b382176a6c.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "a710fc6f89dea79cc8641ee1807fb7c8ff570657a910e5d09ca905f1e2677dc0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0b5897310af6ec037e77305ec29c111c6121381d5ad4d0936eee20ec42fae877", "generation_seconds_batch": 19.37193110701628, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6869438886642456, "target_z": 0.46289060822024797, "ce": 6.252951145172119, "genuineness": 4.306513786315918, "identity": 0.35317832231521606, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a710fc6f89dea79cc8641ee1807fb7c8ff570657a910e5d09ca905f1e2677dc0.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "a780b6672e9cc390088fbb1e9dee7f84804d4633b903dd1000fc1756397cae5f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f52e9cd7ce606752aaa1339302b7a1ec23e2726db5ed77ca6ece8bb7d556286a", "generation_seconds_batch": 16.465363500989042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3393470048904419, "target_z": -0.10644532851703603, "ce": 6.078212261199951, "genuineness": 3.7793264389038086, "identity": 0.2069949060678482, "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_Pleasure_Ecstasy/a780b6672e9cc390088fbb1e9dee7f84804d4633b903dd1000fc1756397cae5f.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "a810169cee10b6356012bbac6b73de2a644160e380986a6f66c151b8f627614a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a89faaf5b72cd62267b711db6ab55898775be859b90f4d562fc36b8984b8a641", "generation_seconds_batch": 21.1163593189558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.7033634185791016, "target_z": 3.7656247681343356, "ce": 5.621508598327637, "genuineness": 3.9550557136535645, "identity": 0.40466395020484924, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a810169cee10b6356012bbac6b73de2a644160e380986a6f66c151b8f627614a.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "a862403d0768c4a34b85e6f0ee7aa6408e166f6f3c40036ad91838efbfc18af1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0ee476c91fcbfe2512469f6265e380a1742f12a60205e6515cacea2b2d06ec01", "generation_seconds_batch": 14.731536427047104, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.072102665901184, "target_z": 1.0937499267792639, "ce": 5.982900142669678, "genuineness": 4.331617832183838, "identity": 0.00953735038638115, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a862403d0768c4a34b85e6f0ee7aa6408e166f6f3c40036ad91838efbfc18af1.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": "a89c7bd4421c52786ee2479c8b93f7a730e3dae4cca7152023d405189d3ba21e", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a513452d4e8a21afd3e8f42be7f7b37522ac9b485eb3ef79e753e4206ddcfde5", "generation_seconds_batch": 17.567151222960092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07522109150886536, "target_z": -0.539062481694816, "ce": 6.459460258483887, "genuineness": 4.337893962860107, "identity": 0.6759071350097656, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even tijd hebt.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a89c7bd4421c52786ee2479c8b93f7a730e3dae4cca7152023d405189d3ba21e.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "6067540b6917c7a703c8122beec75ccbba2be80b48d0678759571d58ca9d5583", "generation_seconds_batch": 15.288596911006607, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": -0.01540452241897583, "target_z": -0.6875, "ce": 6.078212261199951, "genuineness": 4.306513786315918, "identity": 0.7770965099334717, "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_Pleasure_Ecstasy/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.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": "a8dc84cb91a26705d669f2402f32b7fd9a0cfc85731d22bf4deeb7c9cb5ab7a2", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0fa0f5bb583181cf6bfc2aacf1215d44d62f335411c3cb21d3497cae6201859c", "generation_seconds_batch": 17.534504601033404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1961166858673096, "target_z": 1.296874987796544, "ce": 6.3641486167907715, "genuineness": 4.193545341491699, "identity": 0.40806782245635986, "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_Pleasure_Ecstasy/a8dc84cb91a26705d669f2402f32b7fd9a0cfc85731d22bf4deeb7c9cb5ab7a2.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "a8ef85b146f4e4678e8c68c41e48b863a297490f99c64e4705dcf2cbdd257915", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f4d9cb3464bad5ea43236f0977c9bdf2cf32e74c465106903f208cd2c43b296e", "generation_seconds_batch": 20.325607487000525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8836968541145325, "target_z": 0.785156253050864, "ce": 5.959072113037109, "genuineness": 4.137060642242432, "identity": 0.6136893033981323, "hypothesis": "La porte 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_Pleasure_Ecstasy/a8ef85b146f4e4678e8c68c41e48b863a297490f99c64e4705dcf2cbdd257915.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "a91466fd616b2b232b57b34264d605c59ab9c9a71ee5c0db1bef626cf99dbc5f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "81c25533741d6bcd580e4f4bc0e364c36126250ea113429d4851d8ccd7f37e98", "generation_seconds_batch": 24.551556656952016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.983862042427063, "target_z": 0.9492188323733282, "ce": 6.173524379730225, "genuineness": 4.570107460021973, "identity": 0.6813769340515137, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a91466fd616b2b232b57b34264d605c59ab9c9a71ee5c0db1bef626cf99dbc5f.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "a9484695db6ccb7a89ca34522839c4dde82d3ae1fa96d322bf581d287f95cf5c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ea2116a88bbe56817f59777ebdb2033b753207c4a4abe0e2e5fe730fa59f8f9b", "generation_seconds_batch": 20.379085892927833, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.596777319908142, "target_z": 1.9531251098311042, "ce": 6.157639026641846, "genuineness": 4.394378662109375, "identity": 0.5515495538711548, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a9484695db6ccb7a89ca34522839c4dde82d3ae1fa96d322bf581d287f95cf5c.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "c2b8c5670d6bdd7e8f03e4bbee6df03ba1b11ee7c39753affaf1013b0b70b9ad", "generation_seconds_batch": 16.854311750037596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28270602226257324, "target_z": -0.19921873474567997, "ce": 6.308549880981445, "genuineness": 4.457139015197754, "identity": 0.8087626695632935, "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_Pleasure_Ecstasy/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "a9788be55029b6b84cb1f5c287bf015c8d6862cd60205d7a629583947b88e582", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f1bf75a63ba219910bc15be20c92950812c3de0f6a6fa76388d3d200060f1e18", "generation_seconds_batch": 23.178063485072926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3105911016464233, "target_z": 1.4843749389827199, "ce": 6.062326908111572, "genuineness": 4.381826400756836, "identity": 0.7279794216156006, "hypothesis": "La porte 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_Pleasure_Ecstasy/a9788be55029b6b84cb1f5c287bf015c8d6862cd60205d7a629583947b88e582.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "a9b1aeb38e426fe53a858cde2da531b2ae4776f1237db8806f365c49e79d9db9", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "63739b7292259de21de8c698aea0d1e4867152f579d31ab99dfa01fb76d99ba7", "generation_seconds_batch": 23.705036693951115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4727632999420166, "target_z": 1.750000048813824, "ce": 5.903473377227783, "genuineness": 3.8797430992126465, "identity": 0.6063680648803711, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/a9b1aeb38e426fe53a858cde2da531b2ae4776f1237db8806f365c49e79d9db9.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": "a9fcdb0ebe4932d98fbc4ef449efeaa7dbe4181c2f2e5a29bc7bd89a78bd55f5", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ecac8fc12264dbc8b407992d8c5f132486d6fae44ee1592c7116a34a4c81cde2", "generation_seconds_batch": 15.852086842991412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9647829532623291, "target_z": 0.9179688079664161, "ce": 6.308549880981445, "genuineness": 4.344170093536377, "identity": 0.40754956007003784, "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_Pleasure_Ecstasy/a9fcdb0ebe4932d98fbc4ef449efeaa7dbe4181c2f2e5a29bc7bd89a78bd55f5.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "aa35ab37f0bd0f28851d27e0b8ce07392ea23a0d3b73a9b4b9d30989cbcbfde1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "45a5e4e59590eeb3d4273dea977a923e3ed0b002eceac7fa7736584393b9f43a", "generation_seconds_batch": 24.234475665027276, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8431538343429565, "target_z": 0.718750024406912, "ce": 6.141753673553467, "genuineness": 4.375550270080566, "identity": 0.4579947292804718, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/aa35ab37f0bd0f28851d27e0b8ce07392ea23a0d3b73a9b4b9d30989cbcbfde1.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "aa413076c2bc9ce6595106daaf50d2b92d2db5c65fbd665b248447f8f5c57533", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ed4937d714848534af73431b12ccdcf203cff2aa234dc633311daa299fd80699", "generation_seconds_batch": 21.403481506975368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7971075773239136, "target_z": 2.281250073220736, "ce": 5.998785495758057, "genuineness": 4.293961524963379, "identity": 0.4484415054321289, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/aa413076c2bc9ce6595106daaf50d2b92d2db5c65fbd665b248447f8f5c57533.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "aa4913c3619a4aa2214ed95b4a223537e48e24afab98d2bbb31b655f7ed07f0b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e8ab612fb519e7d49acbe3334b8b96aefb7842415d3f5bcb1c6433ff3af2efb8", "generation_seconds_batch": 20.771253459970467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9218549728393555, "target_z": 0.8476562042370399, "ce": 6.300607204437256, "genuineness": 4.444586753845215, "identity": 0.8206501007080078, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/aa4913c3619a4aa2214ed95b4a223537e48e24afab98d2bbb31b655f7ed07f0b.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "aa9fccb6e05554bb4decdfb9b916d284fb6f768c66a26e4c967535cff85dcd55", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a2fb5bf2ebb3c79ba7e2d40c76aafb3e93eac7f0f1b9c93a6590ff4142b15cb5", "generation_seconds_batch": 20.582040712004527, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7644526362419128, "target_z": 0.589843746949136, "ce": 6.221180438995361, "genuineness": 4.005263805389404, "identity": 0.4022413492202759, "hypothesis": "The 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_Pleasure_Ecstasy/aa9fccb6e05554bb4decdfb9b916d284fb6f768c66a26e4c967535cff85dcd55.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": "ab569e0774d2779f150192609034f323adce4f9c1a9e7a8117f18ef3e969b516", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "89e60ba2eb9b7a8f589696e0a266cd1433e8882eb7dea9511cead40cfd544150", "generation_seconds_batch": 16.193890271009877, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6547479629516602, "target_z": 0.410156253050864, "ce": 6.427689552307129, "genuineness": 4.482243061065674, "identity": 0.5435795783996582, "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_Pleasure_Ecstasy/ab569e0774d2779f150192609034f323adce4f9c1a9e7a8117f18ef3e969b516.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": "ab59dab332fd32c09119c6bc087f9d9d2b600c1c16ede17aefe22922864ee178", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a5a6a5ac73b147aa3c35412425e5e0419e727fa2b8e44da3a592804e5f35c27", "generation_seconds_batch": 16.05777452804614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5325226783752441, "target_z": 0.2099609977545641, "ce": 6.125868320465088, "genuineness": 4.306513786315918, "identity": 0.5864238739013672, "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_Pleasure_Ecstasy/ab59dab332fd32c09119c6bc087f9d9d2b600c1c16ede17aefe22922864ee178.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "a4836928ca182d115a67160ba325db17e35944c56d69c875c8dd7b5200e83cca", "generation_seconds_batch": 17.258051809039898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06091177463531494, "target_z": -0.5625, "ce": 6.332377910614014, "genuineness": 4.042920112609863, "identity": 0.458401083946228, "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_Pleasure_Ecstasy/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.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": "ab7eaf70a6373ffc39a6e428f7f201851e2eecf30e1d89d2f8b8987966a06c16", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97e3719deeffb774bc808c5c225e3b59505ec38b0bea0814e4b7c6d348879d88", "generation_seconds_batch": 20.752569730044343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6654798984527588, "target_z": 0.42773430635555987, "ce": 6.348263263702393, "genuineness": 4.582659721374512, "identity": 0.40257567167282104, "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_Pleasure_Ecstasy/ab7eaf70a6373ffc39a6e428f7f201851e2eecf30e1d89d2f8b8987966a06c16.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "abc52fb15e65781ba8667babc538bad389e05b9007b09f8d4d2f9b37f1384b67", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "54c1dc752ba926937b710eb0b1b00eef45ee48b7d860ee61f2608e7dd651d05f", "generation_seconds_batch": 20.736891248030588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9886317253112793, "target_z": 0.9570311920335839, "ce": 6.23706579208374, "genuineness": 4.281409740447998, "identity": 0.4800710380077362, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/abc52fb15e65781ba8667babc538bad389e05b9007b09f8d4d2f9b37f1384b67.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "ac135c33011b9ad4f0a070aeeccb269aeeefb289f136ee482bbef67e0d7e85ff", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ff9a38b597cd015164b70650ee93cc139520d6ce4e3959ce13500fb7bf18161c", "generation_seconds_batch": 20.947192445979454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4679934978485107, "target_z": 1.742187493898272, "ce": 6.340320587158203, "genuineness": 4.218649387359619, "identity": 0.43505415320396423, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ac135c33011b9ad4f0a070aeeccb269aeeefb289f136ee482bbef67e0d7e85ff.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "ac40e746bc6c91dc0f711f70829c0567fa6dad63c734508dc05fcbd5916e0df5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "37f35e1026bcab8974790882b7334d41da8110c4e3ba75f74a71990cb5bd3466", "generation_seconds_batch": 21.394220271962695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.415526032447815, "target_z": 1.656249975593088, "ce": 6.1894097328186035, "genuineness": 4.758388519287109, "identity": 0.38574841618537903, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ac40e746bc6c91dc0f711f70829c0567fa6dad63c734508dc05fcbd5916e0df5.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "ac5a7edfcde59ba9b77a43b15b5e25adebc15c7323de83a05ea703340ebbc766", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "06f8449f7cf365bc41f584198cc5037660b920f5dc922c8c0f023f38566f736b", "generation_seconds_batch": 20.97270651801955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2151957750320435, "target_z": 1.328125012203456, "ce": 6.221180438995361, "genuineness": 4.243753433227539, "identity": 0.42698216438293457, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ac5a7edfcde59ba9b77a43b15b5e25adebc15c7323de83a05ea703340ebbc766.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "ac8c132f2b5a215c3b77d65f68560841403969169acad91876abd1f04759ba5a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "dfd8fb26b88714c5d24ae733393509682568de099e0119a410fd63769bdb2cfe", "generation_seconds_batch": 20.39951921592001, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7310642600059509, "target_z": 0.535156253050864, "ce": 6.109982967376709, "genuineness": 4.507347106933594, "identity": 0.33473873138427734, "hypothesis": "Die Tür ist noch offen! Ich hab deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ac8c132f2b5a215c3b77d65f68560841403969169acad91876abd1f04759ba5a.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "aca8288bde98126e20c3e83d3ab3e2b288e77f2f735657680504af700a4c26ee", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "1f446bd4c26b2e76921e798f3dfcc3ab3aa0735fb13f63dfc46088769bd1d796", "generation_seconds_batch": 23.163376873009838, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6110866069793701, "target_z": 1.9765625793224642, "ce": 6.117925643920898, "genuineness": 4.137060642242432, "identity": 0.48923641443252563, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/aca8288bde98126e20c3e83d3ab3e2b288e77f2f735657680504af700a4c26ee.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "ace819ac0c92e158aa0072a9bfea123023cf7563f8ad34a2a0a8bed4d9f59b15", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "40b20ebdfbc0f1867cc97f712e8d8f19918b5c4ffc291e504b62fdcbb9eeb15b", "generation_seconds_batch": 23.18087616597768, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2104259729385376, "target_z": 1.320312457287904, "ce": 5.982900142669678, "genuineness": 4.105680465698242, "identity": 0.0811997577548027, "hypothesis": "Dee, er staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ace819ac0c92e158aa0072a9bfea123023cf7563f8ad34a2a0a8bed4d9f59b15.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "ad8f235031b620acc905f9cec32c7e95b84be22640699c96b892b7652e5c0505", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3c2adc77530d620afd5e5b1ee809a1b86b65c6b25d5df737df648ad4cf9f254d", "generation_seconds_batch": 22.54853291006293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7859165668487549, "target_z": 0.6249999511861759, "ce": 6.149696350097656, "genuineness": 4.18099308013916, "identity": 0.4222124218940735, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ad8f235031b620acc905f9cec32c7e95b84be22640699c96b892b7652e5c0505.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "adaf6df3115d011c5f75e624b368f63c7189dc3ae7ace36fe8f8c24d91f407fc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "46ebf6275865949aff43c007ae17358015343796325c995b349a0d9421b593c7", "generation_seconds_batch": 19.334609408979304, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1198004484176636, "target_z": 1.1718750854241922, "ce": 6.268836498260498, "genuineness": 4.20609712600708, "identity": 0.4754084348678589, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/adaf6df3115d011c5f75e624b368f63c7189dc3ae7ace36fe8f8c24d91f407fc.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "e43fe4ddbe6d80686005f5af40647bfde6a7886bc49b95202c4113bc75df6578", "generation_seconds_batch": 15.161828021053225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.0322931706905365, "target_z": -0.609374987796544, "ce": 6.165581703186035, "genuineness": 4.306513786315918, "identity": 0.6046506762504578, "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_Pleasure_Ecstasy/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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "7f57b2691096ff8b8cff4d1d6e34c70e1b7be665745a2d7066731246dfddb4da", "generation_seconds_batch": 15.45344557100907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09191527962684631, "target_z": -0.51171873474568, "ce": 6.403861999511719, "genuineness": 3.9425034523010254, "identity": 0.27350476384162903, "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_Pleasure_Ecstasy/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "ae5d8eba0bb2123ac6270cde1fe2f0b1a1e3977cb2fcc3e71eae263c107b69b0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e04073e8b2aeb5e11a53c2485116a4b3a17506cf1d05ab06b884bde995c286b4", "generation_seconds_batch": 17.293376330984756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.663554072380066, "target_z": 2.062500097627648, "ce": 6.252951145172119, "genuineness": 4.331617832183838, "identity": 0.8193112015724182, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ae5d8eba0bb2123ac6270cde1fe2f0b1a1e3977cb2fcc3e71eae263c107b69b0.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": "ae8fbeee6cf9c7a1e034c2bd8efd9002fdbfeb9dd1e04f61fab5f79f43b6e26b", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c9d9e0437d156728e633e8cdc5ec355e8c57f336ec8003c242f8641ad733303f", "generation_seconds_batch": 21.110705318977125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4708137512207031, "target_z": 0.10888670311432197, "ce": 6.078212261199951, "genuineness": 4.293961524963379, "identity": 0.49114662408828735, "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_Pleasure_Ecstasy/ae8fbeee6cf9c7a1e034c2bd8efd9002fdbfeb9dd1e04f61fab5f79f43b6e26b.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "aea155da2b1f2127fdb7f2f369fb3cc1cb8b646087ea05f595473f2ad73fb186", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "86ee043e1203a986991568ae1eb8864441b923c5c8b91fea0e9aa97f1f82252d", "generation_seconds_batch": 19.562309146975167, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1818073987960815, "target_z": 1.273437518305184, "ce": 6.133810997009277, "genuineness": 4.494794845581055, "identity": 0.6185993552207947, "hypothesis": "BI trouver la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.10526315789473684, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/aea155da2b1f2127fdb7f2f369fb3cc1cb8b646087ea05f595473f2ad73fb186.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "b0288c7627596397347dd53e22e27375b21f0b2defbe561bd80ee8c491b998cd", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "786c0a2eb19155f77cca5b311f3f99c5da5a926adfd677a3a975558c2ab2a5c6", "generation_seconds_batch": 20.15748583804816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27197402715682983, "target_z": -0.21679688567802402, "ce": 6.340320587158203, "genuineness": 4.419482707977295, "identity": 0.6295864582061768, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b0288c7627596397347dd53e22e27375b21f0b2defbe561bd80ee8c491b998cd.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": "b08263d99211fc1b9bb5f5d64403e1df141cd6b97046892ed53a36636896d6d1", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "796684721c3b314fec6a83dad8e5e6a01a4b69f6d4c6c558879e6f31ade3a459", "generation_seconds_batch": 15.962766260025091, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16465424001216888, "target_z": -0.392578126525432, "ce": 6.24500846862793, "genuineness": 4.469690799713135, "identity": 0.7478969693183899, "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_Pleasure_Ecstasy/b08263d99211fc1b9bb5f5d64403e1df141cd6b97046892ed53a36636896d6d1.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "b0d58d5ec3cd6a31ee2150437c8ea96aad963246d5948ed15a1e81c6fa0e46c5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f156b11954b9d808e6d268ea748381d05e818aeba522520fac92f5d664cb229a", "generation_seconds_batch": 23.02353993395809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.663554072380066, "target_z": 2.062500097627648, "ce": 6.348263263702393, "genuineness": 4.174716949462891, "identity": 0.4328455924987793, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b0d58d5ec3cd6a31ee2150437c8ea96aad963246d5948ed15a1e81c6fa0e46c5.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "b1254e88e78ce83915fc77f87c258834c0201ff1f1d65ecfb2d220f8eb42c9eb", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b4f3167179b97bc9a4cd127f4e2db157732344aa112131ad34ac43c06da55aaa", "generation_seconds_batch": 20.97270651801955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2867423295974731, "target_z": 1.445312554915552, "ce": 6.157639026641846, "genuineness": 3.9927117824554443, "identity": 0.4678128957748413, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b1254e88e78ce83915fc77f87c258834c0201ff1f1d65ecfb2d220f8eb42c9eb.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "b15254e40c2a956862b8d2b237bcf96d6134341b5caea6e76e7cd9aa54dcb151", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5eabdef129cdfc174fb9f013ae7065736ceb6e67fba744f0638eaf1ba86848de", "generation_seconds_batch": 21.261153049068525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.739870309829712, "target_z": 2.1875, "ce": 6.372091293334961, "genuineness": 4.231201171875, "identity": 0.6744418144226074, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b15254e40c2a956862b8d2b237bcf96d6134341b5caea6e76e7cd9aa54dcb151.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "b158d56606be371e8dfe239796b61dfcd5ed686498dcd27c8af2ecff8918b974", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "faa97750bfd4582283e7ab18bb62f3050ba50a124276560665e0f1d77ce4fdd8", "generation_seconds_batch": 15.45686937100254, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0959515571594238, "target_z": 1.132812506101728, "ce": 5.9431867599487305, "genuineness": 3.9425034523010254, "identity": 0.6475839614868164, "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_Pleasure_Ecstasy/b158d56606be371e8dfe239796b61dfcd5ed686498dcd27c8af2ecff8918b974.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "b1c4d5f059af965bac24f3b27b52f0c7288329b92c74a6c42d28ca71d985a46c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ad3bab553146da6c0bfd0382e5a0acb10d24d5c429e1d38325d4b941530db834", "generation_seconds_batch": 21.01279872097075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1436492204666138, "target_z": 1.21093746949136, "ce": 5.998785495758057, "genuineness": 3.9550557136535645, "identity": 0.44418734312057495, "hypothesis": "The door is still open! I put your code on the chair. Tell me when you are ready.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b1c4d5f059af965bac24f3b27b52f0c7288329b92c74a6c42d28ca71d985a46c.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "b200d9f69b5288141d9962f3d8719ac80923ec1e90aeac00f8de1a78278837a2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e839b4e8758c25ba6f5c38d59b99d7a14b6187ea0e487aae4d3baf92d27aca40", "generation_seconds_batch": 20.08693754998967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8216898441314697, "target_z": 0.683593722542224, "ce": 6.149696350097656, "genuineness": 4.595211505889893, "identity": 0.6860013008117676, "hypothesis": "La porte 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_Pleasure_Ecstasy/b200d9f69b5288141d9962f3d8719ac80923ec1e90aeac00f8de1a78278837a2.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "b271271b80d880fa46ac3ffc094cb0069f694f1080e4aa1adf0566015cb70f58", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7474110c948fdc98517039eee74225f0326bac5312b68929c76ac754d231411e", "generation_seconds_batch": 19.918491133954376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7572979927062988, "target_z": 0.578125012203456, "ce": 6.181467056274414, "genuineness": 4.482243061065674, "identity": 0.6937705278396606, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b271271b80d880fa46ac3ffc094cb0069f694f1080e4aa1adf0566015cb70f58.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "b3104b0b5ae76b0db2e34b40801c474a496d8dcc3df6e277e4efa7c1fc021fd1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e9c45ace8afc8fc75ecf921d0a045c9e2bb89041afa22f7de29ab0d0a5479bcf", "generation_seconds_batch": 20.53139939403627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3105911016464233, "target_z": 1.4843749389827199, "ce": 6.316492557525635, "genuineness": 4.331617832183838, "identity": 0.544657289981842, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b3104b0b5ae76b0db2e34b40801c474a496d8dcc3df6e277e4efa7c1fc021fd1.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "b367a1913efe5e35dbad315ff9e4ebefcb77688396ead41a376f2ca7a9dff63a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ee607515d4544f80fe47b1aa17ccacab36e04119b1e2f9ccb36e4cb624271ada", "generation_seconds_batch": 14.967157692997716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7112517356872559, "target_z": 2.14062506101728, "ce": 6.300607204437256, "genuineness": 4.005263805389404, "identity": 0.5847393274307251, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b367a1913efe5e35dbad315ff9e4ebefcb77688396ead41a376f2ca7a9dff63a.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "b3acf9e41592a7dd7cfcaad8d3ebca3205ab78056c15836890e15f42d43f6009", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "49c424acdf9dc0576af8185ec408b4a32ab67965e7251d47820637b88bd8bf1c", "generation_seconds_batch": 22.00282302906271, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5170208811759949, "target_z": 0.18457029190666796, "ce": 6.181467056274414, "genuineness": 4.193545341491699, "identity": 0.3272296190261841, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b3acf9e41592a7dd7cfcaad8d3ebca3205ab78056c15836890e15f42d43f6009.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": "b3ff1d846dcf0bf126b684961da37e27fafd6a36aeff0c5c87fb3d4180ca3b89", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7cf25905eb9537b3e870a56c6d7f1364e97dcc9987eaf1e14a5fb645424ad642", "generation_seconds_batch": 20.637680758023635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3154981732368469, "target_z": -0.145507810211852, "ce": 6.3641486167907715, "genuineness": 4.545003414154053, "identity": 0.31738555431365967, "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_Pleasure_Ecstasy/b3ff1d846dcf0bf126b684961da37e27fafd6a36aeff0c5c87fb3d4180ca3b89.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "a25e504cf325139331693c991ad1af7488ef03ef56c41c8d84b6a217c2a5cfd4", "generation_seconds_batch": 16.901978828012943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07522109150886536, "target_z": -0.539062481694816, "ce": 6.260893821716309, "genuineness": 4.394378662109375, "identity": 0.5942493677139282, "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_Pleasure_Ecstasy/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.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": "b46a3bd0e10fc8f9b453e7851b445b63ac4eb4e99cef6968a61c9411e9db3440", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f86891c085710f2d2e4e6b22915a2a04ab8ab0dc1ec8d30447fb57829d35f735", "generation_seconds_batch": 15.825683832052164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16703912615776062, "target_z": -0.388671873474568, "ce": 6.006728172302246, "genuineness": 4.419482707977295, "identity": 0.5366994142532349, "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_Pleasure_Ecstasy/b46a3bd0e10fc8f9b453e7851b445b63ac4eb4e99cef6968a61c9411e9db3440.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "b47a738ed2ba33a42faee579cd9b071e6979d9fa48110be1bfca57cf0fb80457", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3e68fa56a49df13b8de5a5c5bded0354731374a58d240a1871606eb06a0d8d65", "generation_seconds_batch": 20.526376878027804, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07999083399772644, "target_z": -0.531250024406912, "ce": 6.022613525390625, "genuineness": 4.268857479095459, "identity": 0.3914567828178406, "hypothesis": "De deur 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_Pleasure_Ecstasy/b47a738ed2ba33a42faee579cd9b071e6979d9fa48110be1bfca57cf0fb80457.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "b566f2e3bdd65890f96224511d799913941b2b6e63ab58ede99c5bb0872f91ad", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0baa7f1364502178279aa73f595c2c843e926b6f22d43d1cbc8c2eb8144fd4fd", "generation_seconds_batch": 21.4190079360269, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5915485620498657, "target_z": 0.3066406814409841, "ce": 6.292664527893066, "genuineness": 4.457139015197754, "identity": 0.23932039737701416, "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_Pleasure_Ecstasy/b566f2e3bdd65890f96224511d799913941b2b6e63ab58ede99c5bb0872f91ad.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "b56d74bf56620e4e688a3a644ce17cb5f97c76a72d01ef8a9f54fc7fe19b3bbc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2ad0532f2aa278a6cd2e0321b2165fdd3bef52ab46d9842ae3e627701333eaa4", "generation_seconds_batch": 19.85450871498324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9409340620040894, "target_z": 0.878906228643952, "ce": 6.070269584655762, "genuineness": 4.262581825256348, "identity": 0.6537594199180603, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b56d74bf56620e4e688a3a644ce17cb5f97c76a72d01ef8a9f54fc7fe19b3bbc.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "b5b8e78fcb4a57dfefa0b855c00363b4edbab0b6b1cc3ace8e787627e364beab", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c64850fe3628b188048933bd0328a2fbaa61ebd4ffc014a6d97f368ee5aa9935", "generation_seconds_batch": 23.870858330046758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1293399333953857, "target_z": 1.1875, "ce": 6.300607204437256, "genuineness": 4.061748504638672, "identity": 0.34888333082199097, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b5b8e78fcb4a57dfefa0b855c00363b4edbab0b6b1cc3ace8e787627e364beab.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": "b5fd3355c85baf68f603a8f14ee7a24921bdb070cf25c22a2e706ff8c383210e", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Your message arrived after I had left.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ebdea49cd95b08333cb260f941717ea2edb801a4a12b22c6d8c0046c619a5c3", "generation_seconds_batch": 16.471577708958648, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2469327449798584, "target_z": -0.257812506101728, "ce": 6.546830177307129, "genuineness": 4.356721878051758, "identity": 0.37329626083374023, "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_Pleasure_Ecstasy/b5fd3355c85baf68f603a8f14ee7a24921bdb070cf25c22a2e706ff8c383210e.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": "b656d3984ec856515c7f20d77853fadbe6709de04f1c02f45d2932e1b0ba00d5", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b7f5af3cfa1d33ec9c65e90a6b8b3fbc878ee4f5780c95328fc468155ba26a27", "generation_seconds_batch": 15.98007430008147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7906863689422607, "target_z": 0.632812506101728, "ce": 6.252951145172119, "genuineness": 4.582659721374512, "identity": 0.697320282459259, "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_Pleasure_Ecstasy/b656d3984ec856515c7f20d77853fadbe6709de04f1c02f45d2932e1b0ba00d5.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "b6a3ec6649d89debaa61f9a1f54b5a9ec017e3e9066033876c254ca841c9f16c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f55a91cb004dbdb2cedea18ed5bb85f0aec2c9a3a61b03f58057b45f9b764fc3", "generation_seconds_batch": 21.12001184502151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2056562900543213, "target_z": 1.3125000976276482, "ce": 6.149696350097656, "genuineness": 3.8546390533447266, "identity": 0.4710105359554291, "hypothesis": "The 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_Pleasure_Ecstasy/b6a3ec6649d89debaa61f9a1f54b5a9ec017e3e9066033876c254ca841c9f16c.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "b6ce8c6fa3fb9d4ee3cd7bc34646d4e3685f64768eba9900044014b383b30016", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0fc93afbc1d941305d9815ffcb580706c5e05b121ca078d44d0b285409c89b59", "generation_seconds_batch": 16.174580728984438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1245701313018799, "target_z": 1.179687445084448, "ce": 6.23706579208374, "genuineness": 4.507347106933594, "identity": 0.47661134600639343, "hypothesis": "La porte 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_Pleasure_Ecstasy/b6ce8c6fa3fb9d4ee3cd7bc34646d4e3685f64768eba9900044014b383b30016.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "b6cea2eceec059075efdda4babc1e436625312813771876b46b79cfae543bb63", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bd72027bce4a1bebc2f29e6b5f0399f03002bc303f30df7d2a402ac3b64efe29", "generation_seconds_batch": 20.298610443016514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4870725870132446, "target_z": 1.773437518305184, "ce": 6.197352409362793, "genuineness": 4.632867813110352, "identity": 0.6610977649688721, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b6cea2eceec059075efdda4babc1e436625312813771876b46b79cfae543bb63.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "b6d1f04268238071a73a7f1efe6addc5acb24a6fd64a9b8f32fa5354c8148d28", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f82e0aa1351f7393c150b764efc708d4c2965437f2aa885982626fcbc0475169", "generation_seconds_batch": 20.745537851005793, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4441447257995605, "target_z": 1.7031251098311042, "ce": 6.09409761428833, "genuineness": 4.005263805389404, "identity": 0.07829837501049042, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b6d1f04268238071a73a7f1efe6addc5acb24a6fd64a9b8f32fa5354c8148d28.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "b6e8d6bd7c9f79cb9a6b4d06115268d68b835ca5069533a235451364193431f6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a27449b15a1dea8d1975da21210c74888a6657993ae8b7d74f7b52de3f7750f5", "generation_seconds_batch": 19.33615984302014, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.091181755065918, "target_z": 1.124999951186176, "ce": 6.3641486167907715, "genuineness": 4.099404335021973, "identity": 0.35758593678474426, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b6e8d6bd7c9f79cb9a6b4d06115268d68b835ca5069533a235451364193431f6.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "b79d48e02053b7e89fcbe272fc37c8cbe97612626da292c55d59ef7aeea546fe", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "445c0d5cc3a9c8eaa4753b4cfcd0803066756477d687869dcc423f49d8f81cc4", "generation_seconds_batch": 17.545284545980394, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.140530824661255, "target_z": 2.843749926779264, "ce": 5.752562999725342, "genuineness": 3.760498285293579, "identity": 0.4367503523826599, "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_Pleasure_Ecstasy/b79d48e02053b7e89fcbe272fc37c8cbe97612626da292c55d59ef7aeea546fe.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "b7b85cddcc822fe675ec5f87cd4603d580837c52ec9792b841afe15a50884ace", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc2a42676c1da3ff189286ab571ead94e7bb00c30b9958e94faeeed650ea9863", "generation_seconds_batch": 20.989391522016376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0673329830169678, "target_z": 1.0859375671190081, "ce": 6.229123115539551, "genuineness": 4.362998008728027, "identity": 0.6541469693183899, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b7b85cddcc822fe675ec5f87cd4603d580837c52ec9792b841afe15a50884ace.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": "b7e544cfb6e0d4a8e5acaab442d0dff4c92cf0d709f24392647b1b34cd05a51c", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5020e431bd4eb1884a9d0675095a2678f012ae99a71107d65ee5db82eb692988", "generation_seconds_batch": 15.802343675983138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5229830741882324, "target_z": 0.19433588792345993, "ce": 6.292664527893066, "genuineness": 4.256305694580078, "identity": 0.49281391501426697, "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_Pleasure_Ecstasy/b7e544cfb6e0d4a8e5acaab442d0dff4c92cf0d709f24392647b1b34cd05a51c.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": "b8333129700b94b26d00e3798449b9c84eddef2b2dfa14e660b157e487c24889", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "25408cfc93182b2ae7b9cf8ec56ad143265d87ca41143eff0703c8bfead161f0", "generation_seconds_batch": 23.10895527305547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8503084778785706, "target_z": 0.730468759152592, "ce": 6.252951145172119, "genuineness": 4.250029563903809, "identity": 0.623839259147644, "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_Pleasure_Ecstasy/b8333129700b94b26d00e3798449b9c84eddef2b2dfa14e660b157e487c24889.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "b83704510e8375042d8235a47be17c4dd9a5514692ca0467c30817753bea38d7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9766529b5d03b300752bb921ec6a401c5ab0587bc5867c686f7230df5d5e4df7", "generation_seconds_batch": 20.302951619029045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.692172646522522, "target_z": 2.109375036610368, "ce": 5.982900142669678, "genuineness": 4.080576419830322, "identity": 0.8283488750457764, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b83704510e8375042d8235a47be17c4dd9a5514692ca0467c30817753bea38d7.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "b858908dc0baa4a14ce6688bcf3942e276772d44b9987b4ef2ac7a1b43e2ab00", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "aa4a3744fd4926afe5dd5192e102340f710baf72b714dc33a3438283cb032356", "generation_seconds_batch": 21.60502986307256, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6015470027923584, "target_z": 1.96093746949136, "ce": 6.395919322967529, "genuineness": 4.331617832183838, "identity": 0.654626727104187, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b858908dc0baa4a14ce6688bcf3942e276772d44b9987b4ef2ac7a1b43e2ab00.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": "b859eb56c1b775d33a7e5b496437cccaac35b0d6f1792113b5b75b27338f0481", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Escribí el número en el sobre.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f49b41fae7b4129e551627cf706d0c447bae88c88f37f1aa9305b964af186480", "generation_seconds_batch": 15.72289074701257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4966121912002563, "target_z": 1.7890626281362882, "ce": 6.157639026641846, "genuineness": 4.319066047668457, "identity": 0.5802831649780273, "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_Pleasure_Ecstasy/b859eb56c1b775d33a7e5b496437cccaac35b0d6f1792113b5b75b27338f0481.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": "b8945845df5d7bf6702bd71d19ed14f48babce62b34dfefa71a7b50188001093", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "54fb85db01f9d3688882763f2223e99ae5fa7d835340f26bd6e22f9c17d04d1b", "generation_seconds_batch": 17.762282024952583, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23023855686187744, "target_z": -0.285156253050864, "ce": 6.157639026641846, "genuineness": 4.21237325668335, "identity": 0.2842061221599579, "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_Pleasure_Ecstasy/b8945845df5d7bf6702bd71d19ed14f48babce62b34dfefa71a7b50188001093.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "b8a0efcac24f0b7749d557761a07e668987c4a253aa21a7ce41081e9a0259ab5", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "8637598c22de1b537fc2fb800ab14f14a8172d1ed06101ed8c720de5292a4d7f", "generation_seconds_batch": 15.914144921931438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12053388357162476, "target_z": -0.464843746949136, "ce": 6.109982967376709, "genuineness": 4.3504462242126465, "identity": 0.5476436018943787, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b8a0efcac24f0b7749d557761a07e668987c4a253aa21a7ce41081e9a0259ab5.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "b8a8bede1b20a18fdc7f745798ff19db0d616fc779f1cb324928070570c95503", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4472eac99eb876a257286bc0d9585b7cdc72d46567d7194aa9b7ba71a62a4818", "generation_seconds_batch": 21.171675069024786, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1961166858673096, "target_z": 1.296874987796544, "ce": 6.284721851348877, "genuineness": 4.381826400756836, "identity": 0.47112083435058594, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b8a8bede1b20a18fdc7f745798ff19db0d616fc779f1cb324928070570c95503.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "b947a0d9c10ada61ab31a26d036afe56b0c19f701a922fdb6f22efde5324120d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ad19cedd152ccfadb14e3fce6f2901f7b93c86929e17b6bcc72e944c559b293f", "generation_seconds_batch": 15.686871849000454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6857514381408691, "target_z": 0.46093746949135994, "ce": 6.173524379730225, "genuineness": 3.591045379638672, "identity": 0.33612534403800964, "hypothesis": "The 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_Pleasure_Ecstasy/b947a0d9c10ada61ab31a26d036afe56b0c19f701a922fdb6f22efde5324120d.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "b99d1f213696b9fc9e9e7b064efde0c3e441aedb3858ffe78c92c5ea0f152cc9", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "04c284d9c0c7f6aae26375fa8d7fd564a14223c85a4426df2edb2e1297b73028", "generation_seconds_batch": 20.53882432798855, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2342748641967773, "target_z": 1.359375036610368, "ce": 6.23706579208374, "genuineness": 4.413206577301025, "identity": 0.5304412841796875, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b99d1f213696b9fc9e9e7b064efde0c3e441aedb3858ffe78c92c5ea0f152cc9.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "b9ae7d0e3bb2eb47d32d679a9c096b44e9ce0cf87aa0c77d2e2d4c4f48860f5c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "821bc6fa69c13f8400c4af2986960723b44a4cf7eb3243a14638e7d5f6f6775e", "generation_seconds_batch": 17.467800884973258, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9402005672454834, "target_z": 2.515624963389632, "ce": 5.919358730316162, "genuineness": 3.998987913131714, "identity": 0.543250322341919, "hypothesis": "I found the little box! It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/b9ae7d0e3bb2eb47d32d679a9c096b44e9ce0cf87aa0c77d2e2d4c4f48860f5c.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "ba1a8ef2acfeedfae8dcaf9fab7081ffff3f2469a088273c3215e70687401273", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0dfab179b96e994d248bcd4d43e40a123a3f0c98882d65ae3b89d96c9d27cf34", "generation_seconds_batch": 20.14059146598447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3869074583053589, "target_z": 1.609375036610368, "ce": 6.435632705688477, "genuineness": 4.18099308013916, "identity": 0.40200114250183105, "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_Pleasure_Ecstasy/ba1a8ef2acfeedfae8dcaf9fab7081ffff3f2469a088273c3215e70687401273.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "05b01300eb737207cabdadff7a9615547cdce6b71e85746652b9ad7161d9bb49", "generation_seconds_batch": 16.57223855506163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6547479629516602, "target_z": 0.410156253050864, "ce": 6.09409761428833, "genuineness": 4.582659721374512, "identity": 0.65875244140625, "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_Pleasure_Ecstasy/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "baafa7014e0a25aed2d013b6a5317b6fdbf4cf0e529b1ff62511aa28c537ca02", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b44a948795fefd68b89caf59b9a1f14b53839a0a7938c8e767e01fcc1926cf54", "generation_seconds_batch": 22.402936437050812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9504736661911011, "target_z": 0.8945313384750562, "ce": 6.308549880981445, "genuineness": 4.281409740447998, "identity": 0.4914371073246002, "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_Pleasure_Ecstasy/baafa7014e0a25aed2d013b6a5317b6fdbf4cf0e529b1ff62511aa28c537ca02.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "bad9af7dea6a066577e9e95e679382fcbc7573eadab17990b6bfd0b1e328a73d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "dacae8cba90da392a25cf5a0b425c1d696922983bcd82db586aae701abcb479f", "generation_seconds_batch": 20.01310966699384, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1455751657485962, "target_z": -0.423828126525432, "ce": 6.1894097328186035, "genuineness": 4.595211505889893, "identity": 0.6501080989837646, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/bad9af7dea6a066577e9e95e679382fcbc7573eadab17990b6bfd0b1e328a73d.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "badd496ff3e616243e2cb956271499a363c4d603b3f2fd3f3d477dd1ce03875c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f98572270e7ec876876a3960d22e915d2d8c777066c462a20380dbd6f4da509c", "generation_seconds_batch": 19.428375361021608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9886317253112793, "target_z": 0.9570311920335839, "ce": 6.229123115539551, "genuineness": 4.381826400756836, "identity": 0.3895885944366455, "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_Pleasure_Ecstasy/badd496ff3e616243e2cb956271499a363c4d603b3f2fd3f3d477dd1ce03875c.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "bafd315a46672faff2c1ac90a1f72df4a171619a0d0e665240f3173b7d0e53d5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8cc62b78ad31132c4672947b8d92598a117be2a28f0dfd0bec15298c05af7632", "generation_seconds_batch": 19.330940724001266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7589493989944458, "target_z": 2.218750024406912, "ce": 6.2767791748046875, "genuineness": 3.9425034523010254, "identity": 0.6669391989707947, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/bafd315a46672faff2c1ac90a1f72df4a171619a0d0e665240f3173b7d0e53d5.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "bba10a3ac55bd1efd1411db6be8b8b170adaabb0bd36a897ecf06739467c004f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e86f7301bd011998195076b18313d358364c0303fc45f6896b4d462ab5290758", "generation_seconds_batch": 20.9643388929544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2772027254104614, "target_z": 1.429687445084448, "ce": 5.990842819213867, "genuineness": 4.030367851257324, "identity": 0.43628808856010437, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/bba10a3ac55bd1efd1411db6be8b8b170adaabb0bd36a897ecf06739467c004f.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "bc06d8c0675a0d4bcdbb0bd60695256216c79dbe87b51cd80a66a07ca8503b56", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "bedcf16fa66471424faa5862cb1350660634bf741decaf38095f81b3596279d5", "generation_seconds_batch": 15.513043171958998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3249003887176514, "target_z": 1.5078124084740798, "ce": 6.221180438995361, "genuineness": 4.557555198669434, "identity": 0.6692406535148621, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/bc06d8c0675a0d4bcdbb0bd60695256216c79dbe87b51cd80a66a07ca8503b56.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "bd1cab1ce0d04f05ed690ecde4cc6db3d60f78c0969f28a20538e4ce4b33021f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1f17b405d37d00f7e3971b8d5435bb43a4f3fbc1422ce43237f70147f60a261f", "generation_seconds_batch": 20.212213007034734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0816422700881958, "target_z": 1.109375036610368, "ce": 6.372091293334961, "genuineness": 4.337893962860107, "identity": 0.23663711547851562, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/bd1cab1ce0d04f05ed690ecde4cc6db3d60f78c0969f28a20538e4ce4b33021f.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "bd2b135f3be950feaa7291ccdaf9c9e477a7af35964fe675ae41e0e2d2b4b518", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f9c668eaaade9c94f047fff53921c1fb2e7edf0e952458dc8f5ebd6094ed68fe", "generation_seconds_batch": 20.04487241897732, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48363250494003296, "target_z": 0.12988279800839597, "ce": 6.1020402908325195, "genuineness": 4.532451152801514, "identity": 0.5509787797927856, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/bd2b135f3be950feaa7291ccdaf9c9e477a7af35964fe675ae41e0e2d2b4b518.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "bd4d8723866633dc2c77eb05f8b9e54eccf7e64e4da50544511eafb70789355f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "61fa89643752fa55dbe05337481fec4053558c6a69877d8210823acb44420ed2", "generation_seconds_batch": 19.428375361021608, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6714421510696411, "target_z": 0.4375, "ce": 5.982900142669678, "genuineness": 4.105680465698242, "identity": 0.3366471529006958, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/bd4d8723866633dc2c77eb05f8b9e54eccf7e64e4da50544511eafb70789355f.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "bd8311f808466e192ac489abb825545cf03bba194c0ffe7aae83b7a545ff15fe", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9762173ef50d1c468e35e33a9479fde693497353dd2b99c13de282affa68b924", "generation_seconds_batch": 19.81610798393376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.968819260597229, "target_z": 2.562500097627648, "ce": 6.070269584655762, "genuineness": 4.469690799713135, "identity": 0.5325446128845215, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/bd8311f808466e192ac489abb825545cf03bba194c0ffe7aae83b7a545ff15fe.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "bd8e410f4947993b1c1fc080c97eb490f3e3c3583afba87da32bd2e5b418bc13", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "fde7e256c533dde16e0589a9bd7fd60321707722b285ea23284129bb04870e26", "generation_seconds_batch": 20.493809023988433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.719139814376831, "target_z": 0.5156249633896319, "ce": 6.062326908111572, "genuineness": 3.503180742263794, "identity": 0.22839143872261047, "hypothesis": "The 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_Pleasure_Ecstasy/bd8e410f4947993b1c1fc080c97eb490f3e3c3583afba87da32bd2e5b418bc13.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "bdce51cca58f0396fd62c301c62601bc440e650ec52636a7b4a707c85ae0afd6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f6d208bb508e39116dbb59c89d9f6f28be035287b8087d237a6669d62fbc63dc", "generation_seconds_batch": 20.56486617901828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5776982307434082, "target_z": 1.9218750854241922, "ce": 6.308549880981445, "genuineness": 4.68307638168335, "identity": 0.6119421720504761, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/bdce51cca58f0396fd62c301c62601bc440e650ec52636a7b4a707c85ae0afd6.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "bdfd16aeb38baffce07cc03da06f9a23854cdd5029b33c9a539caedb4b0f711f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8a30d0f5151bf9fb78e90277ca095f252c6eabdeb3a345814ad9d4cfa5bdd302", "generation_seconds_batch": 20.733183413976803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5569677352905273, "target_z": 0.2500000488138241, "ce": 6.173524379730225, "genuineness": 4.193545341491699, "identity": 0.6241581439971924, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/bdfd16aeb38baffce07cc03da06f9a23854cdd5029b33c9a539caedb4b0f711f.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "be19959447e5d134d4924bba8a2718d10b5d10d2d4d8f10bd6865e13ad9084cf", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "c93020760413b892196f95809ee40c15368cff1c472d9e51bbce25ab72fb442d", "generation_seconds_batch": 15.78624447400216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.536696195602417, "target_z": 0.21679688567802402, "ce": 6.221180438995361, "genuineness": 4.080576419830322, "identity": 0.2011098861694336, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/be19959447e5d134d4924bba8a2718d10b5d10d2d4d8f10bd6865e13ad9084cf.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "be2d9179ad8ce57c48d2edce6550a6250b832edccaf4b17000cef9d6f40a0c7f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "87c10499b2491acbb349eb83cb17f31162ecb2f22b53cb5eb3a153d71e7d8a28", "generation_seconds_batch": 20.989391522016376, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0291748046875, "target_z": 1.023437518305184, "ce": 6.324435234069824, "genuineness": 4.595211505889893, "identity": 0.6551403999328613, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/be2d9179ad8ce57c48d2edce6550a6250b832edccaf4b17000cef9d6f40a0c7f.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "be5e42ce9eebd0613e1494f4511830b9d3bee6d67db56ee9874f027c5236f3c9", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "52dc3eb1461773f1f660ba85d01959e289e3771fff972ce9af9b6da50fa508cf", "generation_seconds_batch": 17.0840971339494, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6106275916099548, "target_z": 0.33789060822024797, "ce": 6.141753673553467, "genuineness": 4.570107460021973, "identity": 0.4574947953224182, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/be5e42ce9eebd0613e1494f4511830b9d3bee6d67db56ee9874f027c5236f3c9.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": "be8babc6e6598fdb9b35d4eed61ca6095357905880a6b4ac71c48b2cb1b9511f", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "aa21fc665eb3bbccee33b1a0953f63a0dce29156b23b586aafb05e2f8c7ad13f", "generation_seconds_batch": 22.582418428035453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3101321756839752, "target_z": -0.15429688567802402, "ce": 6.284721851348877, "genuineness": 3.810706615447998, "identity": 0.29353171586990356, "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_Pleasure_Ecstasy/be8babc6e6598fdb9b35d4eed61ca6095357905880a6b4ac71c48b2cb1b9511f.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "be8e43005e48b49dcb6630956ad6a3229b03f07144b4c4be4e7a795544f6ee0c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "280f0d930c2468d13ffa5447aa98f234cf5159c25d3840c8d98ca9a379171041", "generation_seconds_batch": 20.30718487408012, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0244050025939941, "target_z": 1.015624963389632, "ce": 6.372091293334961, "genuineness": 4.457139015197754, "identity": 0.7205525636672974, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/be8e43005e48b49dcb6630956ad6a3229b03f07144b4c4be4e7a795544f6ee0c.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "bf17f27fe91b564cb2e5f3aed11b476c0f375c2e2cb2c57945c74c74a770dfb1", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ec32b775244f7ef8afa0ea1ed94425a2d641613f5fd4cd0f3e6d4c201884f961", "generation_seconds_batch": 16.773008845048025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5784316658973694, "target_z": 0.285156253050864, "ce": 6.483288764953613, "genuineness": 4.457139015197754, "identity": 0.6786060929298401, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/bf17f27fe91b564cb2e5f3aed11b476c0f375c2e2cb2c57945c74c74a770dfb1.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": "bf3172fddc4fa6c2b93819b93f25d77124e34cd3035af5d980aa63c22d88f0fe", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5010990f55c84b814b537d801f0b6f6fcf93470f302261b24ff6a9bba2085db0", "generation_seconds_batch": 15.435156753985211, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7906863689422607, "target_z": 0.632812506101728, "ce": 6.09409761428833, "genuineness": 4.394378662109375, "identity": 0.6057857871055603, "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_Pleasure_Ecstasy/bf3172fddc4fa6c2b93819b93f25d77124e34cd3035af5d980aa63c22d88f0fe.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": "bf62104ed37d080d45054a6ece4297e70f759114e0fa590492e6d18d23402b98", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0c005bd43fdd6cefd34891142a7a4290a12b14340ee76640988bb2acb20ed07a", "generation_seconds_batch": 17.679576912079938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5062888860702515, "target_z": 0.16699214097432394, "ce": 6.435632705688477, "genuineness": 4.344170093536377, "identity": 0.39662879705429077, "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_Pleasure_Ecstasy/bf62104ed37d080d45054a6ece4297e70f759114e0fa590492e6d18d23402b98.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "bfc269ba4e79a6aa00c27a340e61e0d659386904bf6441a6b8c1cf13954e1e63", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ae4df7b687322102299b2008e2ac9ff44f790be80802f1c738766de39e8da5f2", "generation_seconds_batch": 19.63146003196016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7262945175170898, "target_z": 0.5273437957629601, "ce": 6.213237762451172, "genuineness": 4.331617832183838, "identity": 0.12315881997346878, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/bfc269ba4e79a6aa00c27a340e61e0d659386904bf6441a6b8c1cf13954e1e63.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "c10b226512461be7843269268bf361f30feefe0b66e10a66a63993820ee59297", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "0e5e6acca0a704d30309b5bd287ee2ebb20f7d01a284ec7362152e544ac25757", "generation_seconds_batch": 21.11558313795831, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7763770818710327, "target_z": 0.6093750366103681, "ce": 6.284721851348877, "genuineness": 4.469690799713135, "identity": 0.47556233406066895, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c10b226512461be7843269268bf361f30feefe0b66e10a66a63993820ee59297.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "c1cda3985efd5eea0c3328d1915803205f0886c9198368e20cbe7fb89c2156c5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "36f54e1556067e5705cea2165d61f715b71bc126671e634d5a21b208aaaa99d6", "generation_seconds_batch": 19.32586746197194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1627283096313477, "target_z": 1.242187493898272, "ce": 6.292664527893066, "genuineness": 4.6203155517578125, "identity": 0.5927753448486328, "hypothesis": "La porte 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_Pleasure_Ecstasy/c1cda3985efd5eea0c3328d1915803205f0886c9198368e20cbe7fb89c2156c5.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "c1e3c8b3990ae4a621d7bb7dc98a694749bca6cddf10caaff2101b339f6fde0d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "80ddbf8308406582421bf7f35c32a6aab2d3cf389a0614b5071e597c1ef420b3", "generation_seconds_batch": 17.62034638703335, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6511706113815308, "target_z": 0.4042968368641999, "ce": 6.165581703186035, "genuineness": 4.582659721374512, "identity": 0.5233069658279419, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c1e3c8b3990ae4a621d7bb7dc98a694749bca6cddf10caaff2101b339f6fde0d.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "c1ecb4f8b86a632a48de323562ad8340beee3f72aff15e4ff2d5bb6e1bdd4205", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "977b3f0a2f1f526dd533edcc78034d5ceaa28964255cc52ace1e517dab4da886", "generation_seconds_batch": 20.15748583804816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36110907793045044, "target_z": -0.07080079078395002, "ce": 6.260893821716309, "genuineness": 4.413206577301025, "identity": 0.5147218704223633, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c1ecb4f8b86a632a48de323562ad8340beee3f72aff15e4ff2d5bb6e1bdd4205.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": "c302fb6a6a00ea52c7e3ec6b83033a109166c9e11c642824d457b6088538f30e", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ea60ac1d464c9ee3b9041f4675dea636eb99bf8c8128a31414338d3feb63c8af", "generation_seconds_batch": 15.802343675983138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36140719056129456, "target_z": -0.07031250610172801, "ce": 6.24500846862793, "genuineness": 3.9550557136535645, "identity": 0.46461549401283264, "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_Pleasure_Ecstasy/c302fb6a6a00ea52c7e3ec6b83033a109166c9e11c642824d457b6088538f30e.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "c32496b8e9e3aeb20d1625606459cc6147d9588c9adce7d261167f7f4ac62761", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a38b9480f68b3b63e97544327f73b606dd89c96fe1b5069d3409f77bf1b80e41", "generation_seconds_batch": 16.864387554000132, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8543447256088257, "target_z": 2.374999951186176, "ce": 6.268836498260498, "genuineness": 4.419482707977295, "identity": 0.6840888261795044, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c32496b8e9e3aeb20d1625606459cc6147d9588c9adce7d261167f7f4ac62761.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": "c325a70ebaa6e8fbe032b3367841bf9b86d7e6fd1e940a26bde5ddf9ffaa3904", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "37cd12a5e1e1c4508887d1d572690abcfc9d030b574710c472170a5ad67aae1c", "generation_seconds_batch": 15.936360658961348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5975107550621033, "target_z": 0.31640627745777605, "ce": 6.046441555023193, "genuineness": 4.394378662109375, "identity": 0.7887760400772095, "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_Pleasure_Ecstasy/c325a70ebaa6e8fbe032b3367841bf9b86d7e6fd1e940a26bde5ddf9ffaa3904.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "e97641e6fa60654dc6c2cdbcbf3e1ea3cdd7aa6918f68c866e2178e08f2f216b", "generation_seconds_batch": 15.142867924994789, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11695656180381775, "target_z": -0.470703114321976, "ce": 6.3641486167907715, "genuineness": 4.218649387359619, "identity": 0.6470465660095215, "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_Pleasure_Ecstasy/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "c407b15768487fd5dbf13952464ae7ec604e531a5d8c078a7cf2d61a5097b63e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a678e211224fd8f71558d6156164a56437bc08c6ad3e5d1816ecf3f420b80e9f", "generation_seconds_batch": 22.757509530056268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0530236959457397, "target_z": 1.0625000976276482, "ce": 6.086154937744141, "genuineness": 4.2374773025512695, "identity": 0.6700708866119385, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c407b15768487fd5dbf13952464ae7ec604e531a5d8c078a7cf2d61a5097b63e.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "c45e42dbe6e9c77dc132cb45a3bed1a653d697d85de985f1e7a17a6d4d007408", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "11d7fad8ca14b4b5f6e3555bd20b5b65f64dac55447a0b614d1d108f211920b9", "generation_seconds_batch": 21.02502998802811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3307017982006073, "target_z": -0.12060548667382602, "ce": 6.1894097328186035, "genuineness": 3.973883628845215, "identity": 0.36512109637260437, "hypothesis": "The 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_Pleasure_Ecstasy/c45e42dbe6e9c77dc132cb45a3bed1a653d697d85de985f1e7a17a6d4d007408.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "c48f15990afad77b6864b9ace96e0091879d82c0fdf65e67642998b453e038bc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "002a901a9f3bcb3a1008f046cb5e323f4f5098637acd27f07661d4fb2b2c8dd2", "generation_seconds_batch": 16.787366573000327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4441447257995605, "target_z": 1.7031251098311042, "ce": 6.213237762451172, "genuineness": 4.21237325668335, "identity": 0.5384424924850464, "hypothesis": "La porte 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_Pleasure_Ecstasy/c48f15990afad77b6864b9ace96e0091879d82c0fdf65e67642998b453e038bc.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "8cdea0a437c792bfb417ecb5e617cfe05dab529d364036b8ffb210315d8724ee", "generation_seconds_batch": 17.54697629401926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.015598982572555542, "target_z": -0.63671873474568, "ce": 6.181467056274414, "genuineness": 4.362998008728027, "identity": 0.6682456135749817, "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_Pleasure_Ecstasy/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "c49eda2ccb3fc5951da01d0f791ac295b4f0e5041f677fa55d0c822dde2a6309", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "0a2fd0aa801a4a488f82b8e92e596cb2c97837b71644fbf5f186467883b06656", "generation_seconds_batch": 20.13457695604302, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4441447257995605, "target_z": 1.7031251098311042, "ce": 6.109982967376709, "genuineness": 4.268857479095459, "identity": 0.6889997720718384, "hypothesis": "J'ai trouvé la petite botte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c49eda2ccb3fc5951da01d0f791ac295b4f0e5041f677fa55d0c822dde2a6309.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "c4b18b1c8a648f1c6f7bd5417f98008953ad1f788398501fa8c4b0468ae2fbc3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a6a9738bd2dcad67abdd165abd28f8c7bba7b9cc8e3ef3bfc2be02f0fc770f51", "generation_seconds_batch": 19.75718708895147, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6206260919570923, "target_z": 1.992187493898272, "ce": 6.229123115539551, "genuineness": 4.494794845581055, "identity": 0.41118180751800537, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c4b18b1c8a648f1c6f7bd5417f98008953ad1f788398501fa8c4b0468ae2fbc3.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "c4b7eb0d66f5e922efde7c906bea0702b2ae78f423a4edae3a60216dadb0b4f1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8f291a76721f2d373db827fbea7142af2ce502c91f88beb4b5661c6a50b83819", "generation_seconds_batch": 14.526004244107753, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3411356806755066, "target_z": -0.10351562042370399, "ce": 6.324435234069824, "genuineness": 4.507347106933594, "identity": 0.47062060236930847, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c4b7eb0d66f5e922efde7c906bea0702b2ae78f423a4edae3a60216dadb0b4f1.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": "c530de38cade3e76425ef4f5348f6e84b0d4aa85d9eb6e4cb2f39bd63d8d049b", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a3bc8222f75390841db0d2543eef57a60ce7ec7f71c4d011c566d9dc6dd7382e", "generation_seconds_batch": 16.522469925927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0100957155227661, "target_z": 0.992187493898272, "ce": 6.086154937744141, "genuineness": 4.607763767242432, "identity": 0.6231551170349121, "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_Pleasure_Ecstasy/c530de38cade3e76425ef4f5348f6e84b0d4aa85d9eb6e4cb2f39bd63d8d049b.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "c5ba49024fe42f7f8315fce0e2c626c894cb20c343b405ca829b4c50a4f9b551", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8d47bc6de4ad17e3ccdb2de208888fb05cc7864b21fb3ba1726b7f946d7acdef", "generation_seconds_batch": 20.415958989062347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9402005672454834, "target_z": 2.515624963389632, "ce": 5.8875885009765625, "genuineness": 4.494794845581055, "identity": 0.49863526225090027, "hypothesis": "Tengo un grado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.17647058823529413, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c5ba49024fe42f7f8315fce0e2c626c894cb20c343b405ca829b4c50a4f9b551.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "c5d338216db612090f5fe8c07c689f0e830dd0ade74339d68313dfb046267fa2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "869a62b9dbdfee7b2a0fbcc3a65fc61cbb86139af599d10e0828e6a5248501d9", "generation_seconds_batch": 14.745960708009079, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7716072797775269, "target_z": 0.601562481694816, "ce": 6.046441555023193, "genuineness": 3.4718005657196045, "identity": 0.6161919236183167, "hypothesis": "The 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_Pleasure_Ecstasy/c5d338216db612090f5fe8c07c689f0e830dd0ade74339d68313dfb046267fa2.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "c641473d670bedbe1221a5f0cc93324f63a7a7a77e0d1230891600ee7d5d228b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "52567f557dc3409a45cd5a342964fb0379c178665dcb6bfbfe24adc9dcaa1827", "generation_seconds_batch": 16.27537918300368, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.339209794998169, "target_z": 1.5312500732207361, "ce": 6.086154937744141, "genuineness": 4.193545341491699, "identity": 0.6118409633636475, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c641473d670bedbe1221a5f0cc93324f63a7a7a77e0d1230891600ee7d5d228b.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "c65fe9f3ec7305e2bb389f1f0ab470f6e4f9266008e0292a2de484a3726f47d5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b54dd7947497d92d4ab29cc9ef6235c539d19c039a019b3fe5f9c7ae536df7a6", "generation_seconds_batch": 19.372665864997543, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.111912250518799, "target_z": 2.796874987796544, "ce": 5.855817794799805, "genuineness": 3.5973212718963623, "identity": 0.3131956160068512, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c65fe9f3ec7305e2bb389f1f0ab470f6e4f9266008e0292a2de484a3726f47d5.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "c65fec41f7696fd8984b12cf3ccd1fad6db9875b7e629f0096e83b5698d0a829", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "2f90fb893a8b0328f99118995adca243449bc869c2985c9b67f4db799c4d6fb4", "generation_seconds_batch": 15.615963623975404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1865772008895874, "target_z": 1.2812500732207361, "ce": 6.133810997009277, "genuineness": 4.406930446624756, "identity": 0.530586302280426, "hypothesis": "La porte 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_Pleasure_Ecstasy/c65fec41f7696fd8984b12cf3ccd1fad6db9875b7e629f0096e83b5698d0a829.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "c6901f02cbe08793543373da308f553f5730dc92533c2efe69597873387ca14d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5753d20eb668f2e9fc54e496508429537aae5a6723ffdd0878c2078e78d4f27b", "generation_seconds_batch": 18.32615237601567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3172868490219116, "target_z": -0.14257810211851996, "ce": 6.292664527893066, "genuineness": 4.65797233581543, "identity": 0.4236771762371063, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c6901f02cbe08793543373da308f553f5730dc92533c2efe69597873387ca14d.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": "c6bd3bfe60110581d3c37e3e53facd2d72b76c8d6bc187dd1acd65f08a125803", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f357ded7bada38557ab55b661ef3e0180b0876b61732616e20001f42e25238c3", "generation_seconds_batch": 20.525891446042806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38942956924438477, "target_z": -0.024414087669628038, "ce": 6.157639026641846, "genuineness": 4.394378662109375, "identity": 0.5435693264007568, "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_Pleasure_Ecstasy/c6bd3bfe60110581d3c37e3e53facd2d72b76c8d6bc187dd1acd65f08a125803.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": "c6d54efa8a2750e11327836d3f430704695cb1415bdb98af719b8646ab486d7a", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7f762249f8a4f0f67f3b05b589222d466c02a2cf778f6fae6960ceb96c620617", "generation_seconds_batch": 20.525891446042806, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5843938589096069, "target_z": 0.29492184906765595, "ce": 6.292664527893066, "genuineness": 4.093128204345703, "identity": 0.5188657641410828, "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_Pleasure_Ecstasy/c6d54efa8a2750e11327836d3f430704695cb1415bdb98af719b8646ab486d7a.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": "c7c14f32ad7bf6caf2c02331c5e7f3f4f684b81500748d2a5c41c6869c15cd48", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "22927665b5ad2e3eafcc0c584bd08570840e0650624d83516808680771129479", "generation_seconds_batch": 23.878679504035972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10980188846588135, "target_z": -0.48242189788148004, "ce": 6.356205940246582, "genuineness": 4.13078498840332, "identity": 0.46067357063293457, "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_Pleasure_Ecstasy/c7c14f32ad7bf6caf2c02331c5e7f3f4f684b81500748d2a5c41c6869c15cd48.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "c7eda9f0885188fc5e131327cc1eb86335330eedb67a04031c87cfc1f86109da", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c1a3214a855396c6e9847d87a045e706f7c5c95cab23a61976d76eccba445f23", "generation_seconds_batch": 19.554542625905015, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9592796564102173, "target_z": 2.546874987796544, "ce": 6.38797664642334, "genuineness": 4.300237655639648, "identity": 0.6677209138870239, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c7eda9f0885188fc5e131327cc1eb86335330eedb67a04031c87cfc1f86109da.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "c7eef7b19cd5e809c691a3e3e89c4afc5953a82258dceb7164eef10356b50703", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2e366c08fb324f01cd21183c97af83fa9b066f13b34f598044c0f66c826a6c04", "generation_seconds_batch": 16.773008845048025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4579949975013733, "target_z": 0.08789060822024797, "ce": 6.356205940246582, "genuineness": 3.998987913131714, "identity": 0.469128280878067, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c7eef7b19cd5e809c691a3e3e89c4afc5953a82258dceb7164eef10356b50703.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "68d2127a9ff0570dc3caa2ec0e11dc146969c482c2ae785ab4248755fe1a724b", "generation_seconds_batch": 15.161828021053225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3548487722873688, "target_z": -0.08105467148296397, "ce": 6.24500846862793, "genuineness": 4.15588903427124, "identity": 0.6780049800872803, "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_Pleasure_Ecstasy/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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "13d8ec1b1807bdc1e6085b536d6c4fc1ea5fda1da3c4ba25c7e8137980d36371", "generation_seconds_batch": 15.392221463029273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19565773010253906, "target_z": -0.341796885678024, "ce": 6.24500846862793, "genuineness": 4.143336772918701, "identity": 0.45637577772140503, "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_Pleasure_Ecstasy/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "c8944b4bb68fc8b90c9ce31dff380b87099e9747b80b82d531a0eaf47775ce33", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "80d4d4f162bd9480e767eac847046c8f1237a994449860794e2c9b9f095b5a34", "generation_seconds_batch": 20.39951921592001, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1627283096313477, "target_z": 1.242187493898272, "ce": 6.173524379730225, "genuineness": 4.15588903427124, "identity": 0.22167333960533142, "hypothesis": "Die Tür ist noch offen! Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c8944b4bb68fc8b90c9ce31dff380b87099e9747b80b82d531a0eaf47775ce33.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "c89dc2b62cefc6d5e1c4cd14f88bafb4346a11b5486602352fb78b8baccfb8d5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e42b98f74fc3dbcf7f545dff06c3f02799a28b340778cc33a8787562776cd127", "generation_seconds_batch": 23.348525257082656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.062563180923462, "target_z": 1.078125012203456, "ce": 6.078212261199951, "genuineness": 4.356721878051758, "identity": 0.6823567152023315, "hypothesis": "La porte 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_Pleasure_Ecstasy/c89dc2b62cefc6d5e1c4cd14f88bafb4346a11b5486602352fb78b8baccfb8d5.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "c928b072e249d3df72f90ebd373d7843344111494e837ee79322a34a2b94f9a1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3ab7b8149b0f95bfa4c040c63b266754fe582d3a8dfff797dcf1f2362fbd8b64", "generation_seconds_batch": 20.511945129022934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0291748046875, "target_z": 1.023437518305184, "ce": 6.2767791748046875, "genuineness": 4.582659721374512, "identity": 0.6050217151641846, "hypothesis": "La porte 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_Pleasure_Ecstasy/c928b072e249d3df72f90ebd373d7843344111494e837ee79322a34a2b94f9a1.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "c9b9bb7e3e88aab4603ecd26bb401430791f1be66627cb81d935fec1c8f3297d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "53aab8969ffbc02eff49080941b4c317d33c722d7a084de187388a8ff1630ad8", "generation_seconds_batch": 17.855591668980196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1102608442306519, "target_z": 1.156249975593088, "ce": 6.197352409362793, "genuineness": 4.3127899169921875, "identity": 0.6263059377670288, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/c9b9bb7e3e88aab4603ecd26bb401430791f1be66627cb81d935fec1c8f3297d.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "ca2bcb7d0f3701411766169dc95aa4a1b7d46775329a9edf22596aad02dd41ed", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7a6f599baf6ce3b23d7c03d593c7e930cc73643693a7905a91e52551fe7a12af", "generation_seconds_batch": 20.88050187099725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3010516166687012, "target_z": 1.468750024406912, "ce": 6.260893821716309, "genuineness": 4.482243061065674, "identity": 0.5074267387390137, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ca2bcb7d0f3701411766169dc95aa4a1b7d46775329a9edf22596aad02dd41ed.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "caad7e2b449779ff742e93e6c28b9386d78088da2907a0b0ff2f2407a2709566", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "afd5f764a067168527796d53f59138f96deb133641bd31ff8d0d230900fec632", "generation_seconds_batch": 22.149887103005312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8066470623016357, "target_z": 2.296874987796544, "ce": 6.078212261199951, "genuineness": 4.243753433227539, "identity": 0.45392388105392456, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/caad7e2b449779ff742e93e6c28b9386d78088da2907a0b0ff2f2407a2709566.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "cbc01d37e3116d60fd8835a37b9d8162448fb14b09e747aa4a22ae5c10eb443f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "83c6515905205c1179e0eaede610afd09740d4fed54a94c0a467d43ad6901dee", "generation_seconds_batch": 19.83518573397305, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.017983853816986084, "target_z": -0.632812506101728, "ce": 6.133810997009277, "genuineness": 4.306513786315918, "identity": 0.3919655680656433, "hypothesis": "De deur 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_Pleasure_Ecstasy/cbc01d37e3116d60fd8835a37b9d8162448fb14b09e747aa4a22ae5c10eb443f.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "ccd1377f10e0cf2d3133abef084f3dbc9a29654968f70140a09ed03fdf67edca", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ff9c2aaf12d4ccb96855a6e2ff77d6b5a925a092ade55907b512fc5c4eb31a5f", "generation_seconds_batch": 21.446293396060355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9051607847213745, "target_z": 0.8203124572879039, "ce": 6.141753673553467, "genuineness": 4.394378662109375, "identity": 0.12295237183570862, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ccd1377f10e0cf2d3133abef084f3dbc9a29654968f70140a09ed03fdf67edca.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "cce18de371775a9fdd413cf92f95be54fc7557d84d36efad2cf1af29d1cf6bf2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5d3b2891955f0def1dfdfea35249ba03e14e1abbb900d2cca0b874476986f9d7", "generation_seconds_batch": 16.91437904292252, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2295050621032715, "target_z": 1.351562481694816, "ce": 6.0146708488464355, "genuineness": 4.111956596374512, "identity": 0.4491616189479828, "hypothesis": "The door's still open. I put your coat on the chair. Tell me when you are ready.", "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_Pleasure_Ecstasy/cce18de371775a9fdd413cf92f95be54fc7557d84d36efad2cf1af29d1cf6bf2.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "cd7c8a0351d30255aadbbd0ae8434a06eab2ae4afedf3336f17d04ace1252e1b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4bf0c7275dba102a4f133b5407486b352c73c7552e200e846e5bdbde6ab292ed", "generation_seconds_batch": 20.699490900035016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.983862042427063, "target_z": 0.9492188323733282, "ce": 6.173524379730225, "genuineness": 4.645420074462891, "identity": 0.7082570195198059, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/cd7c8a0351d30255aadbbd0ae8434a06eab2ae4afedf3336f17d04ace1252e1b.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "cd86c5e4765aa856773d021b8df1e413cc0d58aa782b8dfaed5cabd812daeb06", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e660647a8f107a9ee64af3076523f1cc7236ca436b87efd649ef4214a506da39", "generation_seconds_batch": 19.80245630000718, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8352657556533813, "target_z": 2.3437501220345602, "ce": 5.95112943649292, "genuineness": 3.7040140628814697, "identity": 0.5126321911811829, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/cd86c5e4765aa856773d021b8df1e413cc0d58aa782b8dfaed5cabd812daeb06.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "cd8813b2542c8a4670dd8969f6269dd2919b34797ae2e41d5af333717a3ad4d6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fc1fe38d88abf9df6cb7cb60523f4e6e0061258b45488abbb9e9ce604d48fd5f", "generation_seconds_batch": 19.519940795958973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.663554072380066, "target_z": 2.062500097627648, "ce": 5.597680568695068, "genuineness": 3.9048471450805664, "identity": 0.4935181736946106, "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_Pleasure_Ecstasy/cd8813b2542c8a4670dd8969f6269dd2919b34797ae2e41d5af333717a3ad4d6.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": "ce1624e066ec0b138e871c5e60c586ba2660fbb35eaae90967aa4e0cfda3c260", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b6240c00b4e1bf60aae56ad3ff540f8580a96d6fd96ffc72604019cae83a00fd", "generation_seconds_batch": 16.21223073604051, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.000556230545044, "target_z": 0.9765625793224642, "ce": 6.1020402908325195, "genuineness": 4.570107460021973, "identity": 0.6586558222770691, "hypothesis": "La carretera gira a la izquierda tras el puente. Sigue hasta la pequeña puerta de madera. Te esperaré al otro lado.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ce1624e066ec0b138e871c5e60c586ba2660fbb35eaae90967aa4e0cfda3c260.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "ce5175bd86b2e0522b93d5eada45748a25aff9b54ea549ee65be09b28f6ce07c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "06810768105d3654caf460f253e91d82fdd5e57198652237e31de332fb54691a", "generation_seconds_batch": 21.64669295202475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6416311264038086, "target_z": 0.3886719222883921, "ce": 6.316492557525635, "genuineness": 4.7458367347717285, "identity": 0.5668245553970337, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ce5175bd86b2e0522b93d5eada45748a25aff9b54ea549ee65be09b28f6ce07c.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "cf033b05f087093184c8120b3528c6c786b644fe2efa8eb5e92f919d9fcbfd4f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3a0177671ff47fd4d3bd346dcea7a3b5b7fcc0824137b46ba153b00f1a89104b", "generation_seconds_batch": 19.89433935494162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9147003889083862, "target_z": 0.8359375671190081, "ce": 6.300607204437256, "genuineness": 4.582659721374512, "identity": 0.6668495535850525, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/cf033b05f087093184c8120b3528c6c786b644fe2efa8eb5e92f919d9fcbfd4f.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "3009fb0ad162cb5155d5989117408e28299f9117f0c557fa2cb4df4142ff70f3", "generation_seconds_batch": 16.62567623599898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06329664587974548, "target_z": -0.558593771356048, "ce": 6.372091293334961, "genuineness": 4.3881025314331055, "identity": 0.6185621619224548, "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_Pleasure_Ecstasy/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "cfcabaae7e008a23a2046b5bc87c3e4a1d0001e95115d5cf56333ef658137f5d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ce8619c8efac46c19b386dc5cf281cb528503f2f2fca4ccf15beea97f8281d2c", "generation_seconds_batch": 16.174580728984438, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9910166263580322, "target_z": 0.9609374694913599, "ce": 6.332377910614014, "genuineness": 4.425758361816406, "identity": 0.5292936563491821, "hypothesis": "La porte 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_Pleasure_Ecstasy/cfcabaae7e008a23a2046b5bc87c3e4a1d0001e95115d5cf56333ef658137f5d.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "d08a27cdaaf282be8c7c5ad413db69704faaf4a94babb6d702161194815c3d4a", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "024753695e09c83efac5a412fefafa1df3a9abf9d755b6b55a9e539f115a5cb2", "generation_seconds_batch": 19.603843186981976, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5681586265563965, "target_z": 1.906249975593088, "ce": 6.109982967376709, "genuineness": 3.653805732727051, "identity": 0.5313689708709717, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d08a27cdaaf282be8c7c5ad413db69704faaf4a94babb6d702161194815c3d4a.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "d0dc2c76ea68059818a656bbc11752ced143f833de0a223f1e7d1e67796126d0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "cc36c74f3a99e31d60342a1cdc634d0e12c374e5c8ce04e1517e77460cb50710", "generation_seconds_batch": 15.511275833006948, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2485841512680054, "target_z": 1.382812506101728, "ce": 6.24500846862793, "genuineness": 4.494794845581055, "identity": 0.4558781385421753, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d0dc2c76ea68059818a656bbc11752ced143f833de0a223f1e7d1e67796126d0.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "d0ebc6f7cba869fee42cb9c8419c942749b1e3d1b180b63e8f5b6ce4b9fe057c", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "79b28e0897178dba2d5b8115ef999f23cb41cd3a4718ed97b3965bfe284e2533", "generation_seconds_batch": 17.35491967399139, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.558160126209259, "target_z": 0.25195308991506393, "ce": 6.141753673553467, "genuineness": 4.400654315948486, "identity": 0.4937325417995453, "hypothesis": "La porte 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_Pleasure_Ecstasy/d0ebc6f7cba869fee42cb9c8419c942749b1e3d1b180b63e8f5b6ce4b9fe057c.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ec07edb578a9d9e92af638b593b3cab4c339899449658df8b9fed55e8e752011", "generation_seconds_batch": 15.38880374492146, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08237573504447937, "target_z": -0.527343746949136, "ce": 6.332377910614014, "genuineness": 3.9425034523010254, "identity": 0.43676894903182983, "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_Pleasure_Ecstasy/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "d21fe67fbac433ecfa7588993a98354947a83580cc009c6acf59166685686891", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "212925d4fd782c1ad91c08f98500554efee89043a93761fcb8a2106da269b7f5", "generation_seconds_batch": 14.967157692997716, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.2359261512756348, "target_z": 2.9999998535585277, "ce": 6.356205940246582, "genuineness": 4.18099308013916, "identity": 0.6091780662536621, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d21fe67fbac433ecfa7588993a98354947a83580cc009c6acf59166685686891.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "d22e561a452d1e98d3a7df8623eeb76686c33a5f17ef6aec7b7b14135d8be73c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0961c1237ede6934278b9cc8223176771dbcfb4b38b24b6b1c9e6932519b791d", "generation_seconds_batch": 20.504583336994983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5396772623062134, "target_z": 0.22167963487259593, "ce": 6.403861999511719, "genuineness": 4.570107460021973, "identity": 0.44867032766342163, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d22e561a452d1e98d3a7df8623eeb76686c33a5f17ef6aec7b7b14135d8be73c.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "41e3b540dd2b72df0e1ec18853c54a861fafbf8badbc8bbe5e70c069eb033850", "generation_seconds_batch": 15.256656678044237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41968780755996704, "target_z": 0.025146490286049008, "ce": 6.284721851348877, "genuineness": 4.406930446624756, "identity": 0.5920106768608093, "hypothesis": "Las llaves están en la mesa de la cocina. Miré en el cajón y luego, junto a la ventana, llévatelas cuando te vayas.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.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": "d23d8e71d8eb9f7349173e2a52a48d76d6b9d4d25ad0c78827c51f571ca9afe8", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9bf07404ebca7ca65c335fedc79184a458c278d7e243ccbb0ad296888309ebf3", "generation_seconds_batch": 20.637680758023635, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31967172026634216, "target_z": -0.138671873474568, "ce": 6.268836498260498, "genuineness": 4.381826400756836, "identity": 0.675812304019928, "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_Pleasure_Ecstasy/d23d8e71d8eb9f7349173e2a52a48d76d6b9d4d25ad0c78827c51f571ca9afe8.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "d28796ad42e3cb8e55c842ea98fadb4b33cc17f594005409e90d148afb7f999e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "eccefd47504c79953312d1743551e4a9b6fe7802bb9e1529d775c1927ebd1145", "generation_seconds_batch": 21.149578440003097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.264544725418091, "target_z": 3.0468747925412476, "ce": 5.959072113037109, "genuineness": 4.193545341491699, "identity": 0.42777663469314575, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d28796ad42e3cb8e55c842ea98fadb4b33cc17f594005409e90d148afb7f999e.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "d2ed292a88a0c5847d10f3e3a60ed3866e0132aef9b5d09bcebe69e010b7c826", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d3da589cd85a7f8eaffbdd3d2a4c06e04dff0f14e32be27e2511303d855ac088", "generation_seconds_batch": 16.95383519399911, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.967167854309082, "target_z": 0.9218750854241922, "ce": 6.348263263702393, "genuineness": 4.570107460021973, "identity": 0.6432017087936401, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d2ed292a88a0c5847d10f3e3a60ed3866e0132aef9b5d09bcebe69e010b7c826.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "d31e012d21f8e0f892a4f8db38718fcc8d34dc6434e32ce6180db6dee9199a86", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "3f6d559f1eb33f37cbb84e4e0bc79878c1add40210156dc7662469924858b116", "generation_seconds_batch": 20.97253055893816, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9623980522155762, "target_z": 0.9140625305086401, "ce": 6.284721851348877, "genuineness": 4.432034492492676, "identity": 0.6046640872955322, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d31e012d21f8e0f892a4f8db38718fcc8d34dc6434e32ce6180db6dee9199a86.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "d3a48efe70c0b1e150900adf11217315efab23223bc6777c85127554423d4020", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "afcf342b5377fe2083e5a163622ff97253cd1affbfefa0ea9ea05ff398e95616", "generation_seconds_batch": 22.837404463090934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7167549133300781, "target_z": 0.5117186859318559, "ce": 6.2767791748046875, "genuineness": 4.3127899169921875, "identity": 0.7004499435424805, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d3a48efe70c0b1e150900adf11217315efab23223bc6777c85127554423d4020.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "d3bae4e0591200233264c8a4cb310c6d541247c17744ba97835bcdc37c158f49", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6c9fc1377513eab9eb7ccb7c3b22ffa027facfcadfe6eb0ad63fab2f06916b56", "generation_seconds_batch": 15.808861505007371, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3105911016464233, "target_z": 1.4843749389827199, "ce": 6.395919322967529, "genuineness": 4.381826400756836, "identity": 0.35952532291412354, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d3bae4e0591200233264c8a4cb310c6d541247c17744ba97835bcdc37c158f49.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "c0bee9781c3f9eed33e122f7e996833bd5c2723276e491665c009d7e8401db7a", "generation_seconds_batch": 15.201710833003744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06091177463531494, "target_z": -0.5625, "ce": 6.054384231567383, "genuineness": 4.507347106933594, "identity": 0.756725549697876, "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_Pleasure_Ecstasy/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.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": "d412075856c1afd4f2fefab3bbf6701d25d4e936840486f3a3b1c172f45a8869", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fde981456f161a6684dfd0526cc5b9030cbe8d828ebe9baffe0a71d42ad314ac", "generation_seconds_batch": 16.00560619099997, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8431538343429565, "target_z": 0.718750024406912, "ce": 6.205295085906982, "genuineness": 4.545003414154053, "identity": 0.5689511299133301, "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_Pleasure_Ecstasy/d412075856c1afd4f2fefab3bbf6701d25d4e936840486f3a3b1c172f45a8869.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "d431b390f7add688c0230f9ccee86236c9f762e80b18fbbbbac407ec9f44d9e8", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "258139331ffac3c61bf47d1dbcc61226927b3994d266f6eaa77471d45ed8320a", "generation_seconds_batch": 16.927962858928367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3238452672958374, "target_z": -0.131835936737284, "ce": 6.062326908111572, "genuineness": 3.9299514293670654, "identity": 0.19649694859981537, "hypothesis": "The 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_Pleasure_Ecstasy/d431b390f7add688c0230f9ccee86236c9f762e80b18fbbbbac407ec9f44d9e8.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "d4554a16c4453ef30825acac31384a97cda2babad32438a2517d49dd4de9efe2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "905f06e742ddd3467be09b9825fb3c93d807fa3107b721517a59706300e066c0", "generation_seconds_batch": 19.326638028025627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9218549728393555, "target_z": 0.8476562042370399, "ce": 6.300607204437256, "genuineness": 4.482243061065674, "identity": 0.6555188894271851, "hypothesis": "La porte 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_Pleasure_Ecstasy/d4554a16c4453ef30825acac31384a97cda2babad32438a2517d49dd4de9efe2.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "d51c93bea846b49bec43cdf0e21463add18b9914692593dfa4d6a0b7fcf254e0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "dba143aba2d807e562db7281750fa1bb8bd3a73c361f3f9a4c45515ce1eab614", "generation_seconds_batch": 20.677822713973, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5395400524139404, "target_z": 1.859375036610368, "ce": 6.340320587158203, "genuineness": 4.055472373962402, "identity": 0.6134119629859924, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d51c93bea846b49bec43cdf0e21463add18b9914692593dfa4d6a0b7fcf254e0.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "d5451c7c9e66f6220bb8167bb0c7c3e9c2755f00ee5eac4f5543dd75613883f5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "585216391cb1765134e606b8738486331be6edfb8f208145f5bcfbf9bc195c6e", "generation_seconds_batch": 23.966206943034194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.921121597290039, "target_z": 2.4843751342380163, "ce": 5.597680568695068, "genuineness": 3.71028995513916, "identity": 0.36524641513824463, "hypothesis": "But the door is 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_Pleasure_Ecstasy/d5451c7c9e66f6220bb8167bb0c7c3e9c2755f00ee5eac4f5543dd75613883f5.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "d5bd47638f62f4a9b9acdf6547c7b9c02392c4eb58802a35b485ade5d4c2d868", "bucket": "emo_Pleasure_Ecstasy", "phase": "wording", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "3b9f17f6540239a8a864fbfe5d985daa36bea5f9fd50bf7a6a27368dd62a1070", "generation_seconds_batch": 16.927962858928367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5444470643997192, "target_z": 0.229492189788148, "ce": 6.316492557525635, "genuineness": 3.860914945602417, "identity": 0.2535063624382019, "hypothesis": "The 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_Pleasure_Ecstasy/d5bd47638f62f4a9b9acdf6547c7b9c02392c4eb58802a35b485ade5d4c2d868.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "d5ccf8e9122624adeb0eafa9c7feb9cdaf4318971a928f1c9176f9eb623cb033", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "aea2d333fa5bf36eb26a257669eff8265e644b722b70fe25ff7160cc35aff9bb", "generation_seconds_batch": 20.64067047496792, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09906992316246033, "target_z": -0.5, "ce": 6.23706579208374, "genuineness": 4.457139015197754, "identity": 0.553040623664856, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d5ccf8e9122624adeb0eafa9c7feb9cdaf4318971a928f1c9176f9eb623cb033.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "d64ad34be9b1f7ddfd39a4a364e0944ba24b2300484e46cc061aa0402428569f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "3be9de6d016601086f6e58fbbdd7b84840e836225809045010c26d47159f5dd7", "generation_seconds_batch": 20.57968131196685, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8813120126724243, "target_z": 0.7812500732207361, "ce": 6.483288764953613, "genuineness": 3.9801597595214844, "identity": 0.43414974212646484, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d64ad34be9b1f7ddfd39a4a364e0944ba24b2300484e46cc061aa0402428569f.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": "d67f4ddfada4e46659102f98633a35d2ccc3317c4e6452b6f266401475b9d131", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ae00de910511ab2db7f42b2104aaca5a164c5af424bf4b21ced1dae892dcf6a5", "generation_seconds_batch": 14.796279111993499, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5211944580078125, "target_z": 0.19140627745777605, "ce": 6.332377910614014, "genuineness": 4.381826400756836, "identity": 0.7341729998588562, "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_Pleasure_Ecstasy/d67f4ddfada4e46659102f98633a35d2ccc3317c4e6452b6f266401475b9d131.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "d695c23561bd827526cb9b3e9dc51a2907ad0a2ab924466dba74bbffc7ab3a3d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0e493036a0d3237b7d60de4ca0bbe395ece6d1f05635fb31e0ccb143a5f5d04f", "generation_seconds_batch": 22.837404463090934, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8860816955566406, "target_z": 0.7890624328809919, "ce": 6.109982967376709, "genuineness": 4.1998209953308105, "identity": 0.060033902525901794, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d695c23561bd827526cb9b3e9dc51a2907ad0a2ab924466dba74bbffc7ab3a3d.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "d6b7d083f9251bacd49c3059a53f0309066070971221c7cfc4bc90801d17f198", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3fb2a8adb4580ded43754affeb7c2a2baf2f4c1267f0a2c0d3a122df36017074", "generation_seconds_batch": 19.65980603499338, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0196352005004883, "target_z": 1.0078124084740798, "ce": 6.372091293334961, "genuineness": 4.21237325668335, "identity": 0.4557947814464569, "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_Pleasure_Ecstasy/d6b7d083f9251bacd49c3059a53f0309066070971221c7cfc4bc90801d17f198.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "d82f757d021f982b94891591186df967d7598bdb0d8d11bcb7ebf1e1594d413e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "92012a42af656b9304de314889588ea75b267e0a02f581b491b3d70b37b11ba1", "generation_seconds_batch": 20.711381254019216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6015470027923584, "target_z": 1.96093746949136, "ce": 6.395919322967529, "genuineness": 4.519899368286133, "identity": 0.6604920625686646, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d82f757d021f982b94891591186df967d7598bdb0d8d11bcb7ebf1e1594d413e.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": "d83f2fc2e30c9dd9bcf8b74dba1d87cb2e297fb1706e7da610fc857357d6dc18", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9fae73b73b0cfc0fbfc58c2d09c170346b1eeab9b6d16ac9cbaad78d826b773f", "generation_seconds_batch": 15.304053961997852, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6285142302513123, "target_z": 0.367187493898272, "ce": 6.403861999511719, "genuineness": 4.582659721374512, "identity": 0.5070511102676392, "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_Pleasure_Ecstasy/d83f2fc2e30c9dd9bcf8b74dba1d87cb2e297fb1706e7da610fc857357d6dc18.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "d8496fad6ae2e65bd26ca1aaf3c2e86eb342474379155d518b191579ad8535b0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "68a5f67b3e6af1bf20591d4c43521eaea7f5e4df154e72a4a7a9299b5fb3b047", "generation_seconds_batch": 24.337763041025028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3417319059371948, "target_z": -0.10253905105925998, "ce": 6.062326908111572, "genuineness": 4.193545341491699, "identity": 0.31284016370773315, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d8496fad6ae2e65bd26ca1aaf3c2e86eb342474379155d518b191579ad8535b0.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "d9253b84579271cabde363e434e9cf49d0a049fef5388f4dd2c8ba3e53fb48ee", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a92eaf0a6db4e4fa86998fee7b85f0ec8540671f743ea93aace71d395d0f1748", "generation_seconds_batch": 23.966206943034194, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1722677946090698, "target_z": 1.2578124084740798, "ce": 6.149696350097656, "genuineness": 3.7040140628814697, "identity": 0.3604603409767151, "hypothesis": "The 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_Pleasure_Ecstasy/d9253b84579271cabde363e434e9cf49d0a049fef5388f4dd2c8ba3e53fb48ee.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "d9b446bb96a1fb00a063b205f691596fdf0a57723c361c75d2f1a1cc0acd531d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2f2176b6014dfcfe2910688d29b84b438b65deb1d261b3e2d11b805349662aea", "generation_seconds_batch": 20.932213103980757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1102608442306519, "target_z": 1.156249975593088, "ce": 6.054384231567383, "genuineness": 3.823258876800537, "identity": 0.42995020747184753, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/d9b446bb96a1fb00a063b205f691596fdf0a57723c361c75d2f1a1cc0acd531d.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "da0d9c27c8993ac219a5c2525ece0d5515bb9c37499c59fdff2590223fa0a8cf", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5ae6437ef14ba8064f71e222b938b8123d706ed30388b96d4505594d6f4eca37", "generation_seconds_batch": 23.02353993395809, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.663554072380066, "target_z": 2.062500097627648, "ce": 6.0305562019348145, "genuineness": 4.143336772918701, "identity": 0.3877180814743042, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/da0d9c27c8993ac219a5c2525ece0d5515bb9c37499c59fdff2590223fa0a8cf.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": "da810e9334aed6685f1fcba2a01bf672849b0abae01695671f8e46d29ff5ff08", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ef104cef85c71cf7710cd7f82ae10f144d8c2032acf39d6da58300567472196c", "generation_seconds_batch": 16.09404853801243, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37720704078674316, "target_z": -0.04443361319925803, "ce": 6.443574905395508, "genuineness": 4.18099308013916, "identity": 0.3439139127731323, "hypothesis": "I wrote the number on the envelope, rate it carefully, and check the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/da810e9334aed6685f1fcba2a01bf672849b0abae01695671f8e46d29ff5ff08.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "daed12b4f58717cde32474c6a3cbf1ab80026fd09f907fcaedbe9b09b027b474", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "e629957e148210b157db5f4599bb84015d2008f7c076d364d05ed80039b1bb5d", "generation_seconds_batch": 20.10203339299187, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9862468242645264, "target_z": 0.9531249145758078, "ce": 6.205295085906982, "genuineness": 4.3504462242126465, "identity": 0.0954345315694809, "hypothesis": "De deur 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_Pleasure_Ecstasy/daed12b4f58717cde32474c6a3cbf1ab80026fd09f907fcaedbe9b09b027b474.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "daf034ccce43e31d8c2db4b942286a54040881930758e8f2333597340e5302b5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c595707d04661404d45107ae570b9454bb9b49de06ee0acaddf4248541ee9e39", "generation_seconds_batch": 20.711823081946932, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24931763112545013, "target_z": -0.253906253050864, "ce": 6.173524379730225, "genuineness": 4.293961524963379, "identity": 0.5560846328735352, "hypothesis": "De deur 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_Pleasure_Ecstasy/daf034ccce43e31d8c2db4b942286a54040881930758e8f2333597340e5302b5.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a427aad2678c5b4190778c6b9b05ea9badbb1e1f4b5145179c0c00c57ebe024c", "generation_seconds_batch": 17.258051809039898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.04183271527290344, "target_z": -0.593749975593088, "ce": 6.443574905395508, "genuineness": 4.13078498840332, "identity": 0.49502187967300415, "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_Pleasure_Ecstasy/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "db751c7dd19b26852dd38c2241b4d689a976a330bde0152da45f9d4472b7534f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cf1474863c5b2214a47c7c349b7a7fba45e80b6dbd5d6f97c9e54695aca85134", "generation_seconds_batch": 21.73170935397502, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4107563495635986, "target_z": 1.6484376159328322, "ce": 5.95112943649292, "genuineness": 3.8169827461242676, "identity": 0.5956970453262329, "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_Pleasure_Ecstasy/db751c7dd19b26852dd38c2241b4d689a976a330bde0152da45f9d4472b7534f.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "db7b25cef6303fe6bc5208fb9488ca7062ecd5ef5317c76fc8f48d99fb99e9c0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "754789a12ae313dcb3d9df989479af8d7b17620de6543dab077f87b07347d3a4", "generation_seconds_batch": 21.210105127072893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6356688737869263, "target_z": 0.37890622864395196, "ce": 6.427689552307129, "genuineness": 4.13078498840332, "identity": 0.47052934765815735, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/db7b25cef6303fe6bc5208fb9488ca7062ecd5ef5317c76fc8f48d99fb99e9c0.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": "dbdc02bab5b353146ebadd4248b1262420b14d9110cb9a0bf850caf13e971bac", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da9d31dc4c1dc43bd839f211cca60c1a8baa3554b188ec445060087b91b095dc", "generation_seconds_batch": 15.230912892031483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6320915818214417, "target_z": 0.37304691008493607, "ce": 6.395919322967529, "genuineness": 4.21237325668335, "identity": 0.32883021235466003, "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_Pleasure_Ecstasy/dbdc02bab5b353146ebadd4248b1262420b14d9110cb9a0bf850caf13e971bac.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "dc22d566c47143f84278894944b7a5007a3a2a09293d1d10e9b3f884667cc057", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8f7acdab189e0658de1079646fbcc109decadd03a3a5ac23f71922d05ef83867", "generation_seconds_batch": 20.771253459970467, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3249003887176514, "target_z": 1.5078124084740798, "ce": 6.292664527893066, "genuineness": 4.632867813110352, "identity": 0.6955767869949341, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/dc22d566c47143f84278894944b7a5007a3a2a09293d1d10e9b3f884667cc057.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "dc973500eeeff5d8687c86b4f612f32cc746b0820ddc8452fde69928cb333e55", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "81bf463fa314ec93760ec41491ffe2910e07b29d9b874464bee1b49166d9091f", "generation_seconds_batch": 24.337763041025028, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03944781422615051, "target_z": -0.597656253050864, "ce": 6.300607204437256, "genuineness": 4.532451152801514, "identity": 0.15547506511211395, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/dc973500eeeff5d8687c86b4f612f32cc746b0820ddc8452fde69928cb333e55.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": "dd090e5c5b02961b58fbcc99581672c50a98eaf4bbbe724f675b593220be4293", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "846e8f8afb18b6b55af6e6f04ac18d0295003a107d6ffe380877da4bb426f4de", "generation_seconds_batch": 15.8486776399659, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12888097763061523, "target_z": -0.451171873474568, "ce": 6.300607204437256, "genuineness": 4.344170093536377, "identity": 0.45099133253097534, "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_Pleasure_Ecstasy/dd090e5c5b02961b58fbcc99581672c50a98eaf4bbbe724f675b593220be4293.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "dd59ac65880b6244751fa790e49540223a6d11296f6a2463af6c398be8b1bccd", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "db5472841561fbbef3bda71cf93171fb64c7d34ed850cb18fe2dda09a8a61641", "generation_seconds_batch": 20.41296136705205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48035329580307007, "target_z": 0.124511715317778, "ce": 6.221180438995361, "genuineness": 4.331617832183838, "identity": 0.5742241740226746, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/dd59ac65880b6244751fa790e49540223a6d11296f6a2463af6c398be8b1bccd.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "ddd19706c700b129a3677d63674c0c1b1b908016bb08812ec222e4d6bc2327f8", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8f65fd1b55b32691a43bb593eb4a347eb4751d9b679568f0e081897fd3b7c622", "generation_seconds_batch": 21.02502998802811, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.520002007484436, "target_z": 0.18945313872888803, "ce": 6.213237762451172, "genuineness": 3.6663577556610107, "identity": 0.5426563024520874, "hypothesis": "The 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_Pleasure_Ecstasy/ddd19706c700b129a3677d63674c0c1b1b908016bb08812ec222e4d6bc2327f8.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "de01cecd1728f42dd11536aea72e8d689e52fac457fe8dfc5c51f837c37b34f7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "d0049e3e7d70d67f35179cdd8716e8c54f93e53a485c2d7d2aa2c023b6de34d4", "generation_seconds_batch": 16.457519276998937, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7382189035415649, "target_z": 0.546874987796544, "ce": 6.23706579208374, "genuineness": 4.68307638168335, "identity": 0.21531365811824799, "hypothesis": "De deur 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_Pleasure_Ecstasy/de01cecd1728f42dd11536aea72e8d689e52fac457fe8dfc5c51f837c37b34f7.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "de42f6b72d363c25c69190aa75eeabe5be4d7b710ffbcd833ce9dd1060c26107", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "af08e2c13ead82f7d77eb510305011f4459730d31f1771552ef2d26f508d34f7", "generation_seconds_batch": 20.49244266806636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3439794778823853, "target_z": 1.5390624328809919, "ce": 6.09409761428833, "genuineness": 4.143336772918701, "identity": 0.22589847445487976, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/de42f6b72d363c25c69190aa75eeabe5be4d7b710ffbcd833ce9dd1060c26107.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "de7b6e483e614064ca43f4df6ad859e8d33aa950238d658e821bc8310cef2fcf", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e0faed14e7c78570e96b9ea6678540b4e5c14ef0ed45d1e07c387ca27ffddedd", "generation_seconds_batch": 19.851167022949085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4004596769809723, "target_z": -0.006347652055061994, "ce": 6.395919322967529, "genuineness": 4.011539936065674, "identity": 0.37573736906051636, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/de7b6e483e614064ca43f4df6ad859e8d33aa950238d658e821bc8310cef2fcf.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": "deacd9cc896d86804d0d60359ff2fc341128a3beca3212e846166a845573384f", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "12a129cb4126dfc41ed30115b0c4d3fc24ec24792343f96bbce8c00a7b3aa2e4", "generation_seconds_batch": 15.936360658961348, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7549130916595459, "target_z": 0.57421873474568, "ce": 6.229123115539551, "genuineness": 4.607763767242432, "identity": 0.7745640873908997, "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_Pleasure_Ecstasy/deacd9cc896d86804d0d60359ff2fc341128a3beca3212e846166a845573384f.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "dee74a5a5bfffcc7810a62477ec3dff16dd5894521433d75ba7111794c7b9e5c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "ac4fb70e45b6317fbc643355a1547c08e744eb1b1f4362c40685e417eadf64ce", "generation_seconds_batch": 20.49081054504495, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.197767972946167, "target_z": 2.9374998047447036, "ce": 5.855817794799805, "genuineness": 4.394378662109375, "identity": 0.5599345564842224, "hypothesis": "La porte 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_Pleasure_Ecstasy/dee74a5a5bfffcc7810a62477ec3dff16dd5894521433d75ba7111794c7b9e5c.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "df1e99d707eb695b1031b20e1fb4f2b6d7969d084602b5c5ea5d433e38a953e2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "363e8cf4f6fc6d57400aac4c1c2060b434319e91fcdb87fbb9bc21e4eb2471a4", "generation_seconds_batch": 23.870858330046758, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4823027849197388, "target_z": 1.765624963389632, "ce": 6.395919322967529, "genuineness": 4.444586753845215, "identity": 0.7302923798561096, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/df1e99d707eb695b1031b20e1fb4f2b6d7969d084602b5c5ea5d433e38a953e2.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "dfaae8954e4107c83679b1921376f1473856cdee1a9ab9158936e45111d447e2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "ab91c55f389c98a095b61b051bad98e4b3137483ba9ed135d017741834b5c310", "generation_seconds_batch": 19.43814574391581, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9743224382400513, "target_z": 0.933593722542224, "ce": 6.23706579208374, "genuineness": 4.024092197418213, "identity": 0.45019033551216125, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/dfaae8954e4107c83679b1921376f1473856cdee1a9ab9158936e45111d447e2.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "e08003f7ea923a7e485dc17a85fd61827d7b69b63e91d6b8b38d6ed104f004f4", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7a7f381751663f1d49659dbacce71d63a988b384a740956fe35496c465427c13", "generation_seconds_batch": 23.17132010695059, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9600131511688232, "target_z": 0.910156253050864, "ce": 6.260893821716309, "genuineness": 4.3881025314331055, "identity": 0.6502255797386169, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/e08003f7ea923a7e485dc17a85fd61827d7b69b63e91d6b8b38d6ed104f004f4.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "e0d475af588945fad35bb7776f6cb70ba3719dae50e02e4223577bb04ddf40a7", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "299ce55ae8aaa813cb8a47f44211224e0a7c22133d924379d018ce2c3b7da920", "generation_seconds_batch": 22.85376572003588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.159609794616699, "target_z": 2.8749997559308795, "ce": 6.1020402908325195, "genuineness": 4.65797233581543, "identity": 0.4330655336380005, "hypothesis": "Oh! J'ai trouvé la petite boîte! Elle était près de la vieille fenêtre! Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/e0d475af588945fad35bb7776f6cb70ba3719dae50e02e4223577bb04ddf40a7.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "e1033403a2d6abce9c4fe086f2b92906d8b86f3fdba12114a1fed060b970b53b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a221e6f9fb037a31b8c41edeb47fba17902ed09aac0aa94e9fcfcc11edf16889", "generation_seconds_batch": 19.536207888042554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3916772603988647, "target_z": 1.6171875915259202, "ce": 6.229123115539551, "genuineness": 4.2374773025512695, "identity": 0.33456605672836304, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/e1033403a2d6abce9c4fe086f2b92906d8b86f3fdba12114a1fed060b970b53b.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "e2e66a1da54a266fe3f5ae3032a7852657419e298b163fe094b310c59d14aaa6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a601c52cfc8faed0e7f60c43339ed1913d21eb523d30adab3eed2a1900c7e71f", "generation_seconds_batch": 20.932213103980757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9242398738861084, "target_z": 0.851562481694816, "ce": 6.109982967376709, "genuineness": 4.18099308013916, "identity": 0.1558692306280136, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/e2e66a1da54a266fe3f5ae3032a7852657419e298b163fe094b310c59d14aaa6.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "e3f0ac884629599b38cc63231c99f19a3c6a1af09a52a9079db4bcfb9ad21aa1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "9b1c6c00ee87c53e6328f2c03992e0f28228c0bb974e391d5a8fd0576b303a9b", "generation_seconds_batch": 15.552451168070547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49257582426071167, "target_z": 0.14453124084740798, "ce": 6.24500846862793, "genuineness": 3.8546390533447266, "identity": 0.3284955620765686, "hypothesis": "The 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_Pleasure_Ecstasy/e3f0ac884629599b38cc63231c99f19a3c6a1af09a52a9079db4bcfb9ad21aa1.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": "e47d545c7833510c56bcbc9f12ed107b3058fe7138518a514d94363bf80306ff", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "30ea8a69f88fd5251000cf294d1fc1dd12ce00f92aa2f6154a5bd37bd7faf3b9", "generation_seconds_batch": 17.534504601033404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1245701313018799, "target_z": 1.179687445084448, "ce": 6.475345611572266, "genuineness": 4.005263805389404, "identity": 0.40107718110084534, "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_Pleasure_Ecstasy/e47d545c7833510c56bcbc9f12ed107b3058fe7138518a514d94363bf80306ff.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "e53b7b6cb5f8c24700becd206f2721cc171b8da0ffd613ce0580414100d332ea", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "c2a392327d4be6282114fca5b688d27479ec8134cc7859f74d74e9c321ec202b", "generation_seconds_batch": 15.609294977970421, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.49376827478408813, "target_z": 0.146484379576296, "ce": 6.372091293334961, "genuineness": 4.595211505889893, "identity": 0.64377361536026, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/e53b7b6cb5f8c24700becd206f2721cc171b8da0ffd613ce0580414100d332ea.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": "e55cc96383655094ef1461a7129ae15a482bf8aa665bd7057b07cb664ee0f623", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cab4332c2f5ead102c7bb3db047d081c69df765fd63f0ebb1583db042ba614a2", "generation_seconds_batch": 15.496268370072357, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2008864879608154, "target_z": 1.304687542712096, "ce": 6.395919322967529, "genuineness": 4.557555198669434, "identity": 0.6146910190582275, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/e55cc96383655094ef1461a7129ae15a482bf8aa665bd7057b07cb664ee0f623.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "e5c486bb327212f15e6667cb2637dc7379ace2dca2bb97dcf94be7d5d961ea3c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "f65718831bac2bbc6eb1811a5da1530bb654ea14026f1e4e5eb517e4e6f876fb", "generation_seconds_batch": 20.736891248030588, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2772027254104614, "target_z": 1.429687445084448, "ce": 6.157639026641846, "genuineness": 4.419482707977295, "identity": 0.27808237075805664, "hypothesis": "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_Pleasure_Ecstasy/e5c486bb327212f15e6667cb2637dc7379ace2dca2bb97dcf94be7d5d961ea3c.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "e64a8a4479fe3588c6106b3879d0722d089c2b6b61a75963057823debc0d1459", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "f1832251753119fb8134ca8a6e42c2f295d780909b6607d178d777fe39a0d694", "generation_seconds_batch": 16.787366573000327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8161866664886475, "target_z": 2.312500097627648, "ce": 6.173524379730225, "genuineness": 4.149612903594971, "identity": 0.526427149772644, "hypothesis": "La porte 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_Pleasure_Ecstasy/e64a8a4479fe3588c6106b3879d0722d089c2b6b61a75963057823debc0d1459.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "e6d0afa08bad97adfc005604647e69976db888ab82c340c20a255f6ee80b6eff", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f60d1d41212ce2577c71e98e745f960e24db65a46b167cb85667c1e86e387560", "generation_seconds_batch": 19.48322176700458, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8908514976501465, "target_z": 0.796874987796544, "ce": 6.181467056274414, "genuineness": 4.168440818786621, "identity": 0.11875323951244354, "hypothesis": "De deur staat nog open! Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/e6d0afa08bad97adfc005604647e69976db888ab82c340c20a255f6ee80b6eff.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0823852d3178a853efbce7c527c95aee30a8ad796fba7a4a57726bd537a250c6", "generation_seconds_batch": 15.392221463029273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07045131921768188, "target_z": -0.546874987796544, "ce": 6.427689552307129, "genuineness": 4.15588903427124, "identity": 0.3262316882610321, "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_Pleasure_Ecstasy/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "e722e7db75fb1dc5508d5a4d4531689722ea12fedbdb188dbbfd3f55a07f56ac", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2f72999b905fdedb01426a1133c9d843290653b0fd3f924e0c0981778936c9a0", "generation_seconds_batch": 20.468300423002802, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9600131511688232, "target_z": 0.910156253050864, "ce": 6.3641486167907715, "genuineness": 4.300237655639648, "identity": 0.38739311695098877, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/e722e7db75fb1dc5508d5a4d4531689722ea12fedbdb188dbbfd3f55a07f56ac.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": "e7b0dea3f9b39a813dfe2a8efba3a0ed54a14f67f961d0a5ec63a77cbdca7574", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "caf66b1b6681fefce3c8e2454be7c27dcdf7ab99bdb0c05e38cb6a8dab277b0b", "generation_seconds_batch": 23.878679504035972, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25468361377716064, "target_z": -0.24511720199160403, "ce": 6.23706579208374, "genuineness": 4.250029563903809, "identity": 0.6333323121070862, "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_Pleasure_Ecstasy/e7b0dea3f9b39a813dfe2a8efba3a0ed54a14f67f961d0a5ec63a77cbdca7574.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "e7c776e041db791851a818767a9978a288fb62fe6ab774eea9c390a51e20d71b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7a98202fa26fabc470fdc0d06780723559848882b0deda7724bcf93f273e8ea0", "generation_seconds_batch": 20.42283347598277, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.529541552066803, "target_z": 0.20507815093234405, "ce": 6.1020402908325195, "genuineness": 4.300237655639648, "identity": 0.21039071679115295, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/e7c776e041db791851a818767a9978a288fb62fe6ab774eea9c390a51e20d71b.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": "e7fb3a3955d5f4ff3b1b912a3b9871736fc63ceed62b2d1fd8e6ef69086d2392", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ebd172da7fffffb3112e3ed3c219fc4b5451614f4db7da10221f649ee0b003e", "generation_seconds_batch": 15.230912892031483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6857514381408691, "target_z": 0.46093746949135994, "ce": 6.38003396987915, "genuineness": 3.973883628845215, "identity": 0.5081107020378113, "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_Pleasure_Ecstasy/e7fb3a3955d5f4ff3b1b912a3b9871736fc63ceed62b2d1fd8e6ef69086d2392.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "e83d6dd2db481ec7375821403bd72567f9a01fd2bea65a608eec5e31b78118f6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "79732c56b7ce8064b4af6fc8a98c9506085deba651bd85bdbcd6fdb8ff621752", "generation_seconds_batch": 20.289955877000466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7883014678955078, "target_z": 0.628906228643952, "ce": 6.221180438995361, "genuineness": 4.444586753845215, "identity": 0.45908862352371216, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/e83d6dd2db481ec7375821403bd72567f9a01fd2bea65a608eec5e31b78118f6.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "e9546df0f144ee689dde7d654bbb495d32196d5b90450b7e0efb46a6dc782150", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d8006d4fed18ef58645e0a114fc7a8103b2e9ee632ed514d7776c044ee35c6cb", "generation_seconds_batch": 16.003340975032188, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3153609037399292, "target_z": 1.492187493898272, "ce": 6.419747352600098, "genuineness": 4.162164688110352, "identity": 0.24070249497890472, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/e9546df0f144ee689dde7d654bbb495d32196d5b90450b7e0efb46a6dc782150.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "e97c4825a5d36d1f1263e7151c62f21b870bbe0f9dd763de9401556a6285d757", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "25063519476640f24f5111f4d28b7d0caa5cf1b4a84c65950457c6b3511cdf51", "generation_seconds_batch": 19.43814574391581, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8908514976501465, "target_z": 0.796874987796544, "ce": 6.475345611572266, "genuineness": 3.873466968536377, "identity": 0.46411752700805664, "hypothesis": "Ich habe die kleine Schacht gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0625, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/e97c4825a5d36d1f1263e7151c62f21b870bbe0f9dd763de9401556a6285d757.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "b1e2c4a6c5b6ba173f142757b8d783d1f7c0af51aeba9f97d71e1780e78af6a3", "generation_seconds_batch": 16.62567623599898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06806641817092896, "target_z": -0.55078126525432, "ce": 6.38003396987915, "genuineness": 4.457139015197754, "identity": 0.4947662949562073, "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_Pleasure_Ecstasy/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.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": "e9ea0e61838ead95ccb5907870d969dba5d74f7c7af7c39d05e3848c8e717a2b", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68040e35aacc692045bc038c59f3e3374bb138abcbd55420001306bca0d6a9ff", "generation_seconds_batch": 21.110705318977125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4603798985481262, "target_z": 0.09179688567802402, "ce": 6.229123115539551, "genuineness": 4.444586753845215, "identity": 0.6207871437072754, "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_Pleasure_Ecstasy/e9ea0e61838ead95ccb5907870d969dba5d74f7c7af7c39d05e3848c8e717a2b.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "eaad2771dfc26cb4d5aee7b963bcb02dc6b3b9e7b04b09c0d46284b60f96abfd", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "b6fbeeaa76616d01a4f3c96784ab49ae682ddd929fa0a2e394fca6a4a7057d6e", "generation_seconds_batch": 23.155982555937953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.752528190612793, "target_z": 0.5703124572879039, "ce": 5.95112943649292, "genuineness": 3.7542223930358887, "identity": 0.4808533191680908, "hypothesis": "The 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_Pleasure_Ecstasy/eaad2771dfc26cb4d5aee7b963bcb02dc6b3b9e7b04b09c0d46284b60f96abfd.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "eb85bd299ec1e79f61499d4b417a9f9136f663e6a46c6c4f8b74bcebe2eff0f1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "79bbc90a1cab9458c9817d2b7d44d844d1875cbd6b614c67cfd48246d402b7af", "generation_seconds_batch": 19.54217707097996, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7303308248519897, "target_z": 2.171875085424192, "ce": 6.133810997009277, "genuineness": 4.18099308013916, "identity": 0.38506412506103516, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/eb85bd299ec1e79f61499d4b417a9f9136f663e6a46c6c4f8b74bcebe2eff0f1.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": "ebbd7d15aed6e857d8ae5ce5604019077b304c87b6d9c9baeefe4d21f023656c", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "102f677efe58cc87f86d774386fdf9b1612186baa116fb29db841eb7220f8121", "generation_seconds_batch": 24.352958249044605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9719375371932983, "target_z": 0.9296874450844479, "ce": 6.538887023925781, "genuineness": 4.532451152801514, "identity": 0.3216434121131897, "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_Pleasure_Ecstasy/ebbd7d15aed6e857d8ae5ce5604019077b304c87b6d9c9baeefe4d21f023656c.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "9c6eb35faff8ab0db4bbe4606694ce1977dc8ab76db9d02b1dec85cc94b81a9e", "generation_seconds_batch": 15.248211741098203, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.208774596452713, "target_z": -0.320312506101728, "ce": 6.205295085906982, "genuineness": 4.432034492492676, "identity": 0.7343988418579102, "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_Pleasure_Ecstasy/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "ec0ee50cb66ea2ad51aef4f5375a73a7b7cc9d437ee63ef79b64a8aa1a435f8c", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "383961bec8f1ff53cd7164609664fb5ba97dccd9d619868fdd17084d10d38a26", "generation_seconds_batch": 20.49244266806636, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1579585075378418, "target_z": 1.2343749389827199, "ce": 6.062326908111572, "genuineness": 4.168440818786621, "identity": 0.09194406867027283, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ec0ee50cb66ea2ad51aef4f5375a73a7b7cc9d437ee63ef79b64a8aa1a435f8c.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "ec429a1198c16be718b1f855008f7ece084c1899e0fb93709c94af9aa74172e1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1e0e6f324fc36f222f769c52c7ea5d42edf09c363d8609df4d7ce066f0306d85", "generation_seconds_batch": 20.37799819302745, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6964834332466125, "target_z": 0.478515620423704, "ce": 6.268836498260498, "genuineness": 4.331617832183838, "identity": 0.6058180928230286, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ec429a1198c16be718b1f855008f7ece084c1899e0fb93709c94af9aa74172e1.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "ecf7a0b0b05eb4962c54fc6f45c4d219cef70e1c178ddd2f07277cbba806d455", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "ade8fed8bec2c6c6a00b5847158b00897819350a315841dd656a0f31dadf024b", "generation_seconds_batch": 19.704366652062163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.644474983215332, "target_z": 2.031250073220736, "ce": 5.95112943649292, "genuineness": 4.457139015197754, "identity": 0.5704636573791504, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ecf7a0b0b05eb4962c54fc6f45c4d219cef70e1c178ddd2f07277cbba806d455.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "ee4dfec6204530ee6aabd084768244dc7d11f871d0c0758f4886b1fb97a38121", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e9f64c887cba94e51dc5dda067222ee8472402c62ea06e943bcdddbd990a5569", "generation_seconds_batch": 20.270661474089138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2915120124816895, "target_z": 1.4531249145758078, "ce": 6.443574905395508, "genuineness": 4.287685871124268, "identity": 0.516403317451477, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ee4dfec6204530ee6aabd084768244dc7d11f871d0c0758f4886b1fb97a38121.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "ee851bbaf7dc246aeb702d01117ee1ab43c6d3cbe867dc34fcaa23c0f6ffa821", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "497d5acc8da855f1dde4c5d6f6ef9d6b24ea72aa5c2208f8e5904fae783acc3f", "generation_seconds_batch": 15.686871849000454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.75014328956604, "target_z": 0.5664061798301279, "ce": 6.1020402908325195, "genuineness": 3.8797430992126465, "identity": 0.530816376209259, "hypothesis": "The 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_Pleasure_Ecstasy/ee851bbaf7dc246aeb702d01117ee1ab43c6d3cbe867dc34fcaa23c0f6ffa821.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": "eedde8d7acee06ca1a5af84ef406633e443cf6e733a705be16ca77eb85c5e3ca", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bd04c7422f9e43b49eb1d6ddc5478bcf2b4915033ccf6f1bbf590aa65f1bbb76", "generation_seconds_batch": 15.825683832052164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4051176607608795, "target_z": 0.0012817533925607732, "ce": 6.205295085906982, "genuineness": 4.595211505889893, "identity": 0.6727763414382935, "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_Pleasure_Ecstasy/eedde8d7acee06ca1a5af84ef406633e443cf6e733a705be16ca77eb85c5e3ca.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "ef06776c340d2715cd055a0f8bc8e9df505e1561fe06d0e21a8a20d335eecab9", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c530fa2e836aad08a25fbfcd4550c7e1470c55219a3d8ba98818d90eae60574a", "generation_seconds_batch": 20.68054711201694, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 3.151721715927124, "target_z": 4.499999853558528, "ce": 5.831989288330078, "genuineness": 4.15588903427124, "identity": 0.30316656827926636, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ef06776c340d2715cd055a0f8bc8e9df505e1561fe06d0e21a8a20d335eecab9.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "ef52f15b9ec969c4ce97844449483a0355510fbdc8ba4f4712842cd769265f69", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a882635f69c1741fb7df371314dc1c10b199e8cb6e886f187729d28df433eaaa", "generation_seconds_batch": 20.504583336994983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7477584481239319, "target_z": 0.5625, "ce": 6.427689552307129, "genuineness": 4.432034492492676, "identity": 0.46580249071121216, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ef52f15b9ec969c4ce97844449483a0355510fbdc8ba4f4712842cd769265f69.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": "efbfe5dee92eee65b2ec8c1164f77d94a91ba086519be7844af60e7afc865eab", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I wrote the number on the envelope.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e311410fe21025dc8bdee3814fbbec3858df100ae63d924fe1d1a68922c81c7", "generation_seconds_batch": 22.582418428035453, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4776703119277954, "target_z": 0.12011720199160403, "ce": 6.427689552307129, "genuineness": 4.331617832183838, "identity": 0.5287225842475891, "hypothesis": "I wrote the number on the envelope, read it carefully, and checked the last two digits. Call me when you have a moment.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/efbfe5dee92eee65b2ec8c1164f77d94a91ba086519be7844af60e7afc865eab.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "f03f8e27a3409a7f92fe39329607f9887e28f939f2bac876460c2062e6f55093", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c41a5e46dcba105c31c0d19c0cc2cade2b5b808bf93467ba029e4badbae4f339", "generation_seconds_batch": 15.675224550999701, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3582888841629028, "target_z": 1.5625000976276482, "ce": 5.788304805755615, "genuineness": 4.011539936065674, "identity": 0.5290566086769104, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f03f8e27a3409a7f92fe39329607f9887e28f939f2bac876460c2062e6f55093.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "f0e12f27fe791d42d864991635d8c136895041a144d06883b3a50164cc801268", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f11239771bc4c63270a4a4e14e9483dbcd362e096eb18ae9534f9babcf262e43", "generation_seconds_batch": 20.145487313042395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2666080594062805, "target_z": -0.22558591233037195, "ce": 6.1894097328186035, "genuineness": 4.281409740447998, "identity": 0.6592968106269836, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f0e12f27fe791d42d864991635d8c136895041a144d06883b3a50164cc801268.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "f1652e407b6a23107c13f3af95a827769c7c3fbaab3a50a9a4c471ca30ef0883", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4d866b283fa513c7748422778644b29c946472ec23089090682032d9010d9294", "generation_seconds_batch": 20.731884787091985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5681586265563965, "target_z": 1.906249975593088, "ce": 6.125868320465088, "genuineness": 4.256305694580078, "identity": 0.3772677183151245, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana, vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f1652e407b6a23107c13f3af95a827769c7c3fbaab3a50a9a4c471ca30ef0883.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": "f1a34fd39f6fffb700164e4112a93544caac06b4274fcfb1e84d9c2c78068c23", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1c9c86e33cd36d52465639b544f16fd6d0f32886f6bc5c676f8ff0e7803b19e8", "generation_seconds_batch": 20.568467609002255, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9266247749328613, "target_z": 0.855468759152592, "ce": 6.229123115539551, "genuineness": 4.406930446624756, "identity": 0.6902494430541992, "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_Pleasure_Ecstasy/f1a34fd39f6fffb700164e4112a93544caac06b4274fcfb1e84d9c2c78068c23.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "f1c1efea8c2bb59c0f608697769c3ea1788e17285b9605e30a3d577dab4eb69d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "664464bafe1d7696f4ddddab26bd79f20ca877e069298de82f85e6fa64a61c2c", "generation_seconds_batch": 22.28444484609645, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7780284881591797, "target_z": 2.250000048813824, "ce": 6.197352409362793, "genuineness": 4.557555198669434, "identity": 0.7777103781700134, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f1c1efea8c2bb59c0f608697769c3ea1788e17285b9605e30a3d577dab4eb69d.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "f1cb4ee653e725d268bc8f40f021cc6018380999885ba422923a5f0926b17bfa", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "0baff0508e92752ac5895ae822b8b4359372a0cb3d733eb11f5d28d1ed08149e", "generation_seconds_batch": 20.242286566994153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47647786140441895, "target_z": 0.118164063262716, "ce": 6.1894097328186035, "genuineness": 3.9676074981689453, "identity": 0.3073769211769104, "hypothesis": "The 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_Pleasure_Ecstasy/f1cb4ee653e725d268bc8f40f021cc6018380999885ba422923a5f0926b17bfa.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": "f1d24dfe432c34654737d8488abcb399625ea8bf859861413e30693bac4b2ae9", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "411d03ebc3937b71a4abe86c9045641fb1185e04966e993bce357fcecea56339", "generation_seconds_batch": 24.877125832950696, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9051607847213745, "target_z": 0.8203124572879039, "ce": 6.260893821716309, "genuineness": 4.419482707977295, "identity": 0.46893566846847534, "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_Pleasure_Ecstasy/f1d24dfe432c34654737d8488abcb399625ea8bf859861413e30693bac4b2ae9.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "f1e35968bcfadfe615f053d6cdcbbe9ceb28b702b0035e8872bebb6a087c436d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "faef9d4971ab937a6f7145cae6964de60730a83b239827c5fcc3a5b3bb3536df", "generation_seconds_batch": 23.178063485072926, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4679934978485107, "target_z": 1.742187493898272, "ce": 6.483288764953613, "genuineness": 4.256305694580078, "identity": 0.7186340689659119, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f1e35968bcfadfe615f053d6cdcbbe9ceb28b702b0035e8872bebb6a087c436d.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "f1ffe8057c0706c8f62c1e81ec9c3310a065d50b71623e656c94bb1993607fed", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "36a7da1da23305e6490e36f6319d4deb0f02e2d2eff1a23bbb4e089ea1a5dd35", "generation_seconds_batch": 20.219445734051988, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.697675883769989, "target_z": 0.480468759152592, "ce": 6.125868320465088, "genuineness": 4.65797233581543, "identity": 0.6847334504127502, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f1ffe8057c0706c8f62c1e81ec9c3310a065d50b71623e656c94bb1993607fed.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "8404deda972bb4281c70ded01ad90797b6ac32c489534c53f9beec9f96c35c56", "generation_seconds_batch": 16.854311750037596, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25885719060897827, "target_z": -0.23828121644049594, "ce": 6.213237762451172, "genuineness": 4.632867813110352, "identity": 0.5822975039482117, "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_Pleasure_Ecstasy/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "f24739d0dc281f880e4a041672ed64fd527d20fc672a96d894ab8239221a6bc3", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a51477022065fc9a1ded6f8b9e50a727ad36c70bfea3cf606b82814bd15bb6c9", "generation_seconds_batch": 21.770712733035907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7763770818710327, "target_z": 0.6093750366103681, "ce": 6.467403411865234, "genuineness": 4.055472373962402, "identity": 0.3658257722854614, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f24739d0dc281f880e4a041672ed64fd527d20fc672a96d894ab8239221a6bc3.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-1", "key": "f2ac102a5f1973e57e84b6f5a3f230b34f517f7e78c8aa7835fe9315e16d5238", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "832cdd2d76f2bbf54b8218e7f92c758079c72ee4fe1b3f53c2811ab1d6ed107e", "generation_seconds_batch": 19.432867628056556, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5109214782714844, "target_z": 1.8125000976276482, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.7086800336837769, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f2ac102a5f1973e57e84b6f5a3f230b34f517f7e78c8aa7835fe9315e16d5238.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": "f2b3e6fc9e229ead0f26ccd905cffd4d6882cebbf1ba2bedc1668f12cd43981f", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "39dc4e89737c6ce997817c82f0c76983b64a83ca76f556d786e8e8528f48b288", "generation_seconds_batch": 15.852086842991412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.752528190612793, "target_z": 0.5703124572879039, "ce": 6.221180438995361, "genuineness": 4.243753433227539, "identity": 0.5374566316604614, "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": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f2b3e6fc9e229ead0f26ccd905cffd4d6882cebbf1ba2bedc1668f12cd43981f.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": "f316537d2f3798bf8a5afaf1a1f3577cefaeb69a7588e3a69bbd8a59770cc061", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The keys are on the kitchen table.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3f7fe05a10bafbfccc62298aaa42251c577d63da4f755855eebd7871398280ae", "generation_seconds_batch": 24.352958249044605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9313945770263672, "target_z": 0.8632813140681441, "ce": 6.356205940246582, "genuineness": 4.13078498840332, "identity": 0.3792573809623718, "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_Pleasure_Ecstasy/f316537d2f3798bf8a5afaf1a1f3577cefaeb69a7588e3a69bbd8a59770cc061.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "f31f627c11606637ccb929066883e448b3c3738230cdbecda1437183789456ba", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f4873e1c9410991f522a32fe4ee495db043c10b249a09e6275ca1321adef4ecb", "generation_seconds_batch": 21.424107028986327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37825044989585876, "target_z": -0.042724592404568974, "ce": 6.324435234069824, "genuineness": 4.030367851257324, "identity": 0.11604763567447662, "hypothesis": "The 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_Pleasure_Ecstasy/f31f627c11606637ccb929066883e448b3c3738230cdbecda1437183789456ba.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "f343fa1d944cc50fcd26486c8b15f0f4f57a91a2d133c280e35071acc9a01d5b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a2fad297c9c7ee6609c588c84ebbe9b08a32c25260d1df54d85861ed70399e41", "generation_seconds_batch": 20.145487313042395, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1372280716896057, "target_z": -0.4375, "ce": 6.0305562019348145, "genuineness": 4.3127899169921875, "identity": 0.5355175137519836, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f343fa1d944cc50fcd26486c8b15f0f4f57a91a2d133c280e35071acc9a01d5b.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "f4b4163c7ff5dd23bfe8974c5f106f06250321458cb2e1e33b5fa59810d08aa5", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4e4e5b141164ef1b9ef42944b3ac987e01bb07172b70eb495200ef1d6c92c6cc", "generation_seconds_batch": 15.78624447400216, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9242398738861084, "target_z": 0.851562481694816, "ce": 6.221180438995361, "genuineness": 4.080576419830322, "identity": 0.7955451011657715, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f4b4163c7ff5dd23bfe8974c5f106f06250321458cb2e1e33b5fa59810d08aa5.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "f500f069d7ce31784ea5b943661e17ebe9572b1eff0720e12c91c70567e07f6e", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "f8d14f47513ffedcc64efb3cd4a5d847541d6e2b37d8f3224e0da4ed980995a0", "generation_seconds_batch": 19.614285938907415, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4346051216125488, "target_z": 1.6875, "ce": 5.557967185974121, "genuineness": 3.7165660858154297, "identity": 0.3535762131214142, "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_Pleasure_Ecstasy/f500f069d7ce31784ea5b943661e17ebe9572b1eff0720e12c91c70567e07f6e.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "f52c762231d71ae1b1e7c3285400865775ccfecc28438c7d393b6943e498f980", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3949242dd3df51bb02a2a6b8101965c937c9484121ecb56ce772e8d369069c9b", "generation_seconds_batch": 15.455411802046001, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9433189630508423, "target_z": 0.882812506101728, "ce": 6.252951145172119, "genuineness": 4.086852550506592, "identity": 0.4512230455875397, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f52c762231d71ae1b1e7c3285400865775ccfecc28438c7d393b6943e498f980.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "f64ad90a3f507173c9b48a588b179146f7daf4bb07884db4c2dcc7baf674ef04", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "210308e3461c10c46c3ecc987173c5bb5ba3c01793e65f4c23457fb9ca6f381c", "generation_seconds_batch": 20.238476130994968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.07687246799469, "target_z": 1.101562481694816, "ce": 5.816103935241699, "genuineness": 3.6192874908447266, "identity": 0.4638572037220001, "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_Pleasure_Ecstasy/f64ad90a3f507173c9b48a588b179146f7daf4bb07884db4c2dcc7baf674ef04.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "f6697972c1c0a65d5ccf6b1229a040a19b7f147a9f5c69d5bd787702662affe2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "95365b67addb484806c5ed709e6c100a9dbe3687c86a5ba638ae9d2bce76e10c", "generation_seconds_batch": 19.851167022949085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6356688737869263, "target_z": 0.37890622864395196, "ce": 6.213237762451172, "genuineness": 4.281409740447998, "identity": 0.36197009682655334, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f6697972c1c0a65d5ccf6b1229a040a19b7f147a9f5c69d5bd787702662affe2.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "f672182818bb75aa587143e3cf1051111857ea0ce108242097e3bce358fde8c1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "32b1de4466b8ddb5ce310ea76d8a0b8f9af28fc3ade56e837866966263bdd949", "generation_seconds_batch": 19.536207888042554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1341097354888916, "target_z": 1.195312554915552, "ce": 6.197352409362793, "genuineness": 4.519899368286133, "identity": 0.14843887090682983, "hypothesis": "De deur 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_Pleasure_Ecstasy/f672182818bb75aa587143e3cf1051111857ea0ce108242097e3bce358fde8c1.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "f682224f4c639ab3c31a7d68bd75d6240e4591847d1139f44e4f9a2edacec601", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "1451c0b95dce09836f9b905503082c0da9402908c2dd6643cd167676275830d8", "generation_seconds_batch": 19.68717737402767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9242398738861084, "target_z": 0.851562481694816, "ce": 5.839932441711426, "genuineness": 3.835810661315918, "identity": 0.33767157793045044, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f682224f4c639ab3c31a7d68bd75d6240e4591847d1139f44e4f9a2edacec601.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "f68943a6751e985790a50dab059784e0cc229defc8adebd55e68e90343e7c711", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c80a4eba5677baf854b1ce1d48df1e1bd795d3c81f5e28c8055ded235e2f1603", "generation_seconds_batch": 22.57671688706614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8741573095321655, "target_z": 0.769531240847408, "ce": 5.863759994506836, "genuineness": 3.810706615447998, "identity": 0.5580003261566162, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f68943a6751e985790a50dab059784e0cc229defc8adebd55e68e90343e7c711.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "f6b33d583d5a55a786ded288a9d409c85fcebb40f33e09bb3176911d462073c6", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a13e82aeb91c9e4632230011f45f90bb129871d44cce918974aa8684d88be6f3", "generation_seconds_batch": 14.56677855795715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5156911611557007, "target_z": 1.820312457287904, "ce": 6.221180438995361, "genuineness": 4.3504462242126465, "identity": 0.372061550617218, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f6b33d583d5a55a786ded288a9d409c85fcebb40f33e09bb3176911d462073c6.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "f6bdf525819c0bb3b3692310b28929e220613d29954161e8a9e92efb44531ec4", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bc873d23d5f5fd6a840d501c750ba76d0de9954c6d9912a0f19ed5ad7a269ebd", "generation_seconds_batch": 20.501100067049265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2731664776802063, "target_z": -0.214843746949136, "ce": 6.149696350097656, "genuineness": 4.074300289154053, "identity": 0.5994564294815063, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f6bdf525819c0bb3b3692310b28929e220613d29954161e8a9e92efb44531ec4.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "f746fd5880dc6db442d046881428a57c064fb2c7d8ff89a870253a7d3543124f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "4c268faa3f0c7ebe6e779a0cf12b630efad7a26472923e89ae27226f0b03aca5", "generation_seconds_batch": 19.242013599956408, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0100957155227661, "target_z": 0.992187493898272, "ce": 6.125868320465088, "genuineness": 3.948779582977295, "identity": 0.38797757029533386, "hypothesis": "The door's still open. I put your coat on the chair. Tell me when you are ready.", "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_Pleasure_Ecstasy/f746fd5880dc6db442d046881428a57c064fb2c7d8ff89a870253a7d3543124f.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "f78436531349a91f14cd2f9f1208e88a7d295e0587c407764c86628421d9bd58", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e63c4f80f0896f328128c2529424a42e233de0bddc4554a50c9b5112c200977c", "generation_seconds_batch": 20.6454172199592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0530236959457397, "target_z": 1.0625000976276482, "ce": 6.443574905395508, "genuineness": 4.18099308013916, "identity": 0.36613529920578003, "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_Pleasure_Ecstasy/f78436531349a91f14cd2f9f1208e88a7d295e0587c407764c86628421d9bd58.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "ca65ce50fe7d0b32c770f356aedcfbf3f0143f2ec628a32ca90cfa3e732745cc", "generation_seconds_batch": 16.57223855506163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36856186389923096, "target_z": -0.05859372254222396, "ce": 6.300607204437256, "genuineness": 4.6705241203308105, "identity": 0.7563823461532593, "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_Pleasure_Ecstasy/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.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": "f7b71b13d0f9e5e3c8c46954225b7ac6149c0622da38f37324cc1b1f284170ac", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Someone moved the little blue chair.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "39b478e8fc524f50be18c3477f633ab1cdb3924dda235d25309036793201da85", "generation_seconds_batch": 15.995910958037712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4723043143749237, "target_z": 0.111328126525432, "ce": 6.41180419921875, "genuineness": 4.369274139404297, "identity": 0.5630427002906799, "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_Pleasure_Ecstasy/f7b71b13d0f9e5e3c8c46954225b7ac6149c0622da38f37324cc1b1f284170ac.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": "f7c5173fc6eccc9789ef1b4dbd363aac5948481e37d2c35579da8a40cee93474", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c1227fc9352fe2e3d83d2438d9b3a55affb92aa0b64ea03169bd56c0042b0080", "generation_seconds_batch": 16.05777452804614, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5021153688430786, "target_z": 0.160156253050864, "ce": 6.1894097328186035, "genuineness": 4.507347106933594, "identity": 0.5925549864768982, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí, junto a la estantería alta. La colocaremos después de comer.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f7c5173fc6eccc9789ef1b4dbd363aac5948481e37d2c35579da8a40cee93474.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "f7e46234396e12a7fd6a1d57e0e07db559ce3e35b2f2f1579d60166466b71abd", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "57faa69ff173a7bb2122983068de61c32056eabeae5d8e6efaede25e130a4d67", "generation_seconds_batch": 20.270910598919727, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6142049431800842, "target_z": 0.34375002440691205, "ce": 6.292664527893066, "genuineness": 4.093128204345703, "identity": 0.23849909007549286, "hypothesis": "The 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_Pleasure_Ecstasy/f7e46234396e12a7fd6a1d57e0e07db559ce3e35b2f2f1579d60166466b71abd.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "f7fb2e3c6258a028df569a573af3e5db4aac0561339e230ffbfc05631213dce2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "98a80649adc24c30a5f8c809409276afe1d51ab5f1dd326791274205887fcd91", "generation_seconds_batch": 21.770712733035907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4508403539657593, "target_z": 0.076171873474568, "ce": 6.459460258483887, "genuineness": 4.2249250411987305, "identity": 0.5510401725769043, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f7fb2e3c6258a028df569a573af3e5db4aac0561339e230ffbfc05631213dce2.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_Pleasure_Ecstasy", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": "c00fb881144d958b276933c4eeaac53a9df3d773dd1b160403728cf6d73c7859", "generation_seconds_batch": 16.903221936896443, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13126584887504578, "target_z": -0.44726564483061604, "ce": 6.2767791748046875, "genuineness": 4.645420074462891, "identity": 0.5955823063850403, "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_Pleasure_Ecstasy/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "f8c81d8cc2be34e943a5ebf1344961353be987a105677bdd734b41f18f58bbe2", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "54153776fa8018049b516955295a5fca837bc8e64f1408607cdc33692e46fe95", "generation_seconds_batch": 20.238476130994968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.07687246799469, "target_z": 1.101562481694816, "ce": 6.0146708488464355, "genuineness": 4.074300289154053, "identity": 0.587794303894043, "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_Pleasure_Ecstasy/f8c81d8cc2be34e943a5ebf1344961353be987a105677bdd734b41f18f58bbe2.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": "f8e38d411cba31f8eea5f7e1669f08c13f4171548347b262736483abd349e590", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0fc0aa45188865a379c1ebf6e8e88388aff5d7912d93a4446423e58b84e6d47", "generation_seconds_batch": 15.985609538038261, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7739921808242798, "target_z": 0.605468759152592, "ce": 6.213237762451172, "genuineness": 4.356721878051758, "identity": 0.7144376039505005, "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_Pleasure_Ecstasy/f8e38d411cba31f8eea5f7e1669f08c13f4171548347b262736483abd349e590.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": "f90ad6c917136d801dc44a5f890b382c95d3a974f6cc04601434dd571f1dd6b6", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "de8cbb8c0c352960e9394ed0f9b64a85422741143d2f1a959ca585639982136a", "generation_seconds_batch": 15.960129579994828, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7334491014480591, "target_z": 0.5390624328809919, "ce": 6.0146708488464355, "genuineness": 4.582659721374512, "identity": 0.6186554431915283, "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_Pleasure_Ecstasy/f90ad6c917136d801dc44a5f890b382c95d3a974f6cc04601434dd571f1dd6b6.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": "f914944a1f285337c3056efaa09391195c013b0696e5bbe38c26299cd69ce2cf", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b88e436aa7b0c64a588a8b38a80f80fd3f8cbfc048eb117143deb71a7f7c5105", "generation_seconds_batch": 16.586311761988327, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1579585075378418, "target_z": 1.2343749389827199, "ce": 6.070269584655762, "genuineness": 4.325342178344727, "identity": 0.5898978114128113, "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_Pleasure_Ecstasy/f914944a1f285337c3056efaa09391195c013b0696e5bbe38c26299cd69ce2cf.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-1", "key": "f9d3a840a365d65088941657e805cea7ecebc986d4c4d2bc385005d6ef803b1d", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f406dbaf1a3de41aeada59b7c97b398e38a10cdcd4111d162d9e46a31fc17fe9", "generation_seconds_batch": 14.529642662033439, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2295050621032715, "target_z": 1.351562481694816, "ce": 6.4515180587768555, "genuineness": 3.660081624984741, "identity": 0.4471176266670227, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/f9d3a840a365d65088941657e805cea7ecebc986d4c4d2bc385005d6ef803b1d.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": "fa637a9898e8cd22925b9739399bd695ae108936f6850672ceae3deccc7f56a0", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "eabfc28e56150c73340cb31b45f4fafe9a6ee5dea25b9baeec0d01cc18d59381", "generation_seconds_batch": 15.866696872981265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7477584481239319, "target_z": 0.5625, "ce": 6.157639026641846, "genuineness": 4.582659721374512, "identity": 0.7705459594726562, "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_Pleasure_Ecstasy/fa637a9898e8cd22925b9739399bd695ae108936f6850672ceae3deccc7f56a0.mp3" }, { "id": "emo_Pleasure_Ecstasy-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-fr-0", "key": "fabf0b5c41426a1c10192ce45865444809df98f4131722425045d9ff8d47f7fc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La porte est encore ouverte.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "01b5eaee8bf14265df73b981a0c020e51dfbd983727ee9b268b05cc908dd18fe", "generation_seconds_batch": 19.326638028025627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7716072797775269, "target_z": 0.601562481694816, "ce": 6.086154937744141, "genuineness": 4.356721878051758, "identity": 0.4939028322696686, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/fabf0b5c41426a1c10192ce45865444809df98f4131722425045d9ff8d47f7fc.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "fac4fce4165fd67aa8cc43fef7ccf4cd0633a6e16282dbb0a12bca765cf0cec9", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d1bc2a74c2c4c435ea1e469420d2f233920f3b259589b0361e0b457e5c7e8e26", "generation_seconds_batch": 20.415958989062347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9020425081253052, "target_z": 2.453125109831104, "ce": 5.927301406860352, "genuineness": 4.268857479095459, "identity": 0.34056031703948975, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/fac4fce4165fd67aa8cc43fef7ccf4cd0633a6e16282dbb0a12bca765cf0cec9.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": "fb2c99055ff82953a247cd752f002cfd14daf98a0dbb1013f92e55a380bd6b72", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d167db079d6abdfaada3c42cc1447198febe9b04ab40dc1b2dea82aefac2f09a", "generation_seconds_batch": 22.763662477955222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7930712699890137, "target_z": 0.6367187835595041, "ce": 6.348263263702393, "genuineness": 4.557555198669434, "identity": 0.6286468505859375, "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_Pleasure_Ecstasy/fb2c99055ff82953a247cd752f002cfd14daf98a0dbb1013f92e55a380bd6b72.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": "fb5004c120b0828977ed346f16eca9bcf54e0f173ad57baabeea2376a5e1c627", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "695f4609eb4dabdc1b586a849c9bce2a566bc22854595817fe0d52c36c2737f4", "generation_seconds_batch": 17.567151222960092, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28449466824531555, "target_z": -0.19628907546617202, "ce": 6.1020402908325195, "genuineness": 4.218649387359619, "identity": 0.24890774488449097, "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_Pleasure_Ecstasy/fb5004c120b0828977ed346f16eca9bcf54e0f173ad57baabeea2376a5e1c627.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "fb9ad049db0a9a36724247196a1795cfa9950cc272a0be8e978f936e38835537", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "0ff876f4b6599f9ad5484f8cea896034b7b43e6c04fa597d8b31838fabe87660", "generation_seconds_batch": 15.88257168896962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0864120721817017, "target_z": 1.1171875915259202, "ce": 5.919358730316162, "genuineness": 4.137060642242432, "identity": 0.07069951295852661, "hypothesis": "De deur 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_Pleasure_Ecstasy/fb9ad049db0a9a36724247196a1795cfa9950cc272a0be8e978f936e38835537.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-0", "key": "fb9f6a0f02f3393ea6fa17d1a2f1665ae261f666199e7d700aaa1cd0e8b4e30f", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The door is still open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] I put your coat on the chair.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c16ba312a7a4ba4189e50fb1d163e96678e07979a281d796626eec7838955dad", "generation_seconds_batch": 15.200551163987257, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.415526032447815, "target_z": 1.656249975593088, "ce": 6.109982967376709, "genuineness": 3.6663577556610107, "identity": 0.5842542052268982, "hypothesis": "The 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_Pleasure_Ecstasy/fb9f6a0f02f3393ea6fa17d1a2f1665ae261f666199e7d700aaa1cd0e8b4e30f.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": "fba5def1e52cdd41b26bbde19e464b58ebdaa05e7f8a0dd2a47d021530dab47c", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] The road turns left behind the bridge.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [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": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fbac0ea48bdeb6967dc2c3052b8b9a6a63ddf830171ad08c41ac319a7ae53e34", "generation_seconds_batch": 17.876762942993082, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12888097763061523, "target_z": -0.451171873474568, "ce": 6.348263263702393, "genuineness": 3.973883628845215, "identity": 0.5465542078018188, "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_Pleasure_Ecstasy/fba5def1e52cdd41b26bbde19e464b58ebdaa05e7f8a0dd2a47d021530dab47c.mp3" }, { "id": "emo_Pleasure_Ecstasy-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-en-1", "key": "fc2d3ca62a433421c186c2e5fb7628a4e69ab61a27e89eaa3a7e7adb635cdfbc", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] I found the little box.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] It was beside the old window.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "39e2e85b64dc1df276964cd9a3244f27506cf4a3853166f2f76d731ea6106b4f", "generation_seconds_batch": 20.212213007034734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1293399333953857, "target_z": 1.1875, "ce": 6.356205940246582, "genuineness": 4.262581825256348, "identity": 0.6079145669937134, "hypothesis": "I found a little box. It was beside the old window. We can look inside together.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/fc2d3ca62a433421c186c2e5fb7628a4e69ab61a27e89eaa3a7e7adb635cdfbc.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "fc80dbf543097f9daabf9ab86855c250c7135129e6d02c29d09ef7ffd1d711db", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "c6e4066ee161f8a8677dde284915220ef4c415e524ea5797008f5ad97c9cc534", "generation_seconds_batch": 20.55365276010707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7684890031814575, "target_z": 2.2343751342380163, "ce": 5.919358730316162, "genuineness": 3.735394239425659, "identity": 0.2725188732147217, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás linda.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/fc80dbf543097f9daabf9ab86855c250c7135129e6d02c29d09ef7ffd1d711db.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-1", "key": "fcfddeee3a4e549c1f833ef3227adb225a0b61a2d1ca506250339c39df3ab1c0", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] He encontrado la cajita.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f39b188778b0e64ce2841c89293166a2cf0926001d7b29a6ad506b2a5c619fc7", "generation_seconds_batch": 15.513043171958998, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1293399333953857, "target_z": 1.1875, "ce": 6.395919322967529, "genuineness": 4.68307638168335, "identity": 0.5818948745727539, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/fcfddeee3a4e549c1f833ef3227adb225a0b61a2d1ca506250339c39df3ab1c0.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": "fd3963b01fb26b64dc1b50d293c605ecff44dadd00eee821a36974b547d872e5", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "55d1f9024793703d928d60dc2738097b68b01e5b98655b52870c567e8730daaa", "generation_seconds_batch": 24.64968965400476, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18731063604354858, "target_z": -0.355468759152592, "ce": 6.308549880981445, "genuineness": 4.469690799713135, "identity": 0.5893391966819763, "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_Pleasure_Ecstasy/fd3963b01fb26b64dc1b50d293c605ecff44dadd00eee821a36974b547d872e5.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": "fe4fc8ce16242677dec28279d99b3197cff9e8e0694c87d2d297c0e761ace3d0", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "207b83da4c74972b3e5545ac59e9162ce8f5da676eaaabe4061830eb6b3f4bf2", "generation_seconds_batch": 16.120293727028184, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2666080594062805, "target_z": -0.22558591233037195, "ce": 6.3641486167907715, "genuineness": 4.507347106933594, "identity": 0.3772459030151367, "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_Pleasure_Ecstasy/fe4fc8ce16242677dec28279d99b3197cff9e8e0694c87d2d297c0e761ace3d0.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": "fe87b2c257cd0a9ad015f105bd0ff025161aa3fe4136952f944c3516fb733ba9", "bucket": "emo_Pleasure_Ecstasy", "phase": "heldout", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "86096d36167c65d477a1aebdbe811f94a66fe74012c564c21d4469a512ecd076", "generation_seconds_batch": 23.71434092510026, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9170852899551392, "target_z": 0.8398438445767842, "ce": 6.125868320465088, "genuineness": 4.413206577301025, "identity": 0.7294552326202393, "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_Pleasure_Ecstasy/fe87b2c257cd0a9ad015f105bd0ff025161aa3fe4136952f944c3516fb733ba9.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "ff236ef6ca41ca58610292c614e1f4f11abac3b95f89827c12f8430b4925ad16", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d0b75b6404ba1b14f058a6e4aabe9740cc67ccc13eff0bed983908208d039e79", "generation_seconds_batch": 14.878827093052678, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5872377157211304, "target_z": 1.9375, "ce": 5.998785495758057, "genuineness": 4.193545341491699, "identity": 0.32925987243652344, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ff236ef6ca41ca58610292c614e1f4f11abac3b95f89827c12f8430b4925ad16.mp3" }, { "id": "emo_Pleasure_Ecstasy-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-es-0", "key": "ff56c9327f9787c5d686e63174fef7ae55357fdcab71d962c5fe0788f651206b", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] La puerta sigue abierta.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fa5bc219e12a6bcf67cf482360bc906bf7adfbee25a864e09b000c3802f3011e", "generation_seconds_batch": 15.382442999980412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7684890031814575, "target_z": 2.2343751342380163, "ce": 5.927301406860352, "genuineness": 4.068024158477783, "identity": 0.4607773423194885, "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_Pleasure_Ecstasy/ff56c9327f9787c5d686e63174fef7ae55357fdcab71d962c5fe0788f651206b.mp3" }, { "id": "emo_Pleasure_Ecstasy-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-de-0", "key": "ff66b14f090280db8b49c0b7d03ef0a2e7bf69fd1194ecd88db4396f813f52d1", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Die Tür ist noch offen.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b798a69dfe6afc75ecf9b8938185bfd6fc1c08564873b11ba36669b8ec106207", "generation_seconds_batch": 22.354467274970375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6404386758804321, "target_z": 0.38671878355950406, "ce": 6.3641486167907715, "genuineness": 4.256305694580078, "identity": 0.3931724429130554, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ff66b14f090280db8b49c0b7d03ef0a2e7bf69fd1194ecd88db4396f813f52d1.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-0", "key": "ff74963dd7d3dc93928bea9fdf55526135f26705c880ea730f3ae6978cab71dd", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] De deur staat nog open.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e24f151daa8ae47559306f7f115d945decc006bef6f38ce8a0c52e4f7969ae56", "generation_seconds_batch": 20.41296136705205, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2713778018951416, "target_z": -0.21777345504246803, "ce": 6.1894097328186035, "genuineness": 4.381826400756836, "identity": 0.4479983448982239, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ff74963dd7d3dc93928bea9fdf55526135f26705c880ea730f3ae6978cab71dd.mp3" }, { "id": "emo_Pleasure_Ecstasy-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Pleasure_Ecstasy-nl-1", "key": "ffef515be2e42b794b991a302c8200b2b641ee5c7649f3a2a3fd8fe822643d57", "bucket": "emo_Pleasure_Ecstasy", "phase": "grid", "candidate": "manual-1c5ef4ec2662", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Project an overwhelming sense of blissful release, using vocal texture to convey expansive, uncontained joy.\nSCRIPT:\n(Begin with a breathy intake that immediately suggests an upward rush of sensation.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Allow the mid-range of the voice to bloom with effortless, sustained resonance.) [3.8 seconds duration] Het stond naast het oude raam.\n(Let the final articulation dissolve into a warm, audible exhalation of pure delight.) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d5d35435924aed82abb5109e90f133289638c3d84a3290d4fa3a9b5b19b4e9c7", "generation_seconds_batch": 20.7847654230427, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24454785883426666, "target_z": -0.261718759152592, "ce": 6.197352409362793, "genuineness": 4.231201171875, "identity": 0.7886282205581665, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Pleasure_Ecstasy/ffef515be2e42b794b991a302c8200b2b641ee5c7649f3a2a3fd8fe822643d57.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-0-seed1701-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "bcccbca638cc2642a9e5f0f761e9821ffb53be9728936cfa2e7b257cdd72687c", "task_id": "emo_Pleasure_Ecstasy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.017983853816986084, "target_z": -0.632812506101728, "ce": 6.268836498260498, "genuineness": 4.425758361816406, "identity": 0.34816664457321167, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/02e2416e8fff3da8bf1ccf20.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-0-seed1701-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "336d845809b4230bf620552369e7279e8da16b69dd225d6ccd6b97d286bf7e14", "task_id": "emo_Pleasure_Ecstasy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.044217586517333984, "target_z": -0.589843746949136, "ce": 6.229123115539551, "genuineness": 4.444586753845215, "identity": 0.6363071203231812, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/372cc5f12e865352f31b4009.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-0-seed1701-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "21c3d6d8af137d1f510b39f1790d4338688f00464870bd3ecacc63aebd5fb5c6", "task_id": "emo_Pleasure_Ecstasy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.025138497352600098, "target_z": -0.621093771356048, "ce": 6.260893821716309, "genuineness": 4.381826400756836, "identity": 0.5576807260513306, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/505d8ff117614179dcaead32.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-0-seed1701-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "d6cc5e1836a1cb6e61b6796190f3890615dcb402fbff8a94dbc1c35ac3ec543d", "task_id": "emo_Pleasure_Ecstasy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.013214081525802612, "target_z": -0.640625012203456, "ce": 6.38003396987915, "genuineness": 4.494794845581055, "identity": 0.32253074645996094, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/038dcd3b6c906487b10a5e0b.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-0-seed1702-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "50f5e7f4957a220d70b654730002e95b9a9498414023545ce503c442eba76b69", "task_id": "emo_Pleasure_Ecstasy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.025138497352600098, "target_z": -0.621093771356048, "ce": 5.895530700683594, "genuineness": 4.218649387359619, "identity": 0.553726077079773, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt, sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/3f70c7a9a8ddebc6a338e9f9.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-0-seed1702-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "b6ba85af1b9209c96e166a944540b7b7d074f53e4324b0fa02be2f82aaa65fef", "task_id": "emo_Pleasure_Ecstasy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.0585269033908844, "target_z": -0.566406228643952, "ce": 6.086154937744141, "genuineness": 4.444586753845215, "identity": 0.6300239562988281, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/11e08202f764c1fb8956d17e.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-0-seed1702-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "a44fd426d72be91ee6dfc21567cf60acaa239b075031d846162bfad6b170a58d", "task_id": "emo_Pleasure_Ecstasy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.08237573504447937, "target_z": -0.527343746949136, "ce": 6.2767791748046875, "genuineness": 4.482243061065674, "identity": 0.37837761640548706, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/30d2e968cd179414fb9b6deb.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-0-seed1702-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "88372ef7cdcac3a5774c87c6f1773667a220b4306887386ef38106631d195a6b", "task_id": "emo_Pleasure_Ecstasy-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.00844430923461914, "target_z": -0.648437518305184, "ce": 6.221180438995361, "genuineness": 4.507347106933594, "identity": 0.5956934690475464, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/780921ea6c674d1b89e7af84.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-1-seed1701-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "f86d53d88646fe06e43b13db7839bd05af3cf0cff51a3249ea743e56b85efc46", "task_id": "emo_Pleasure_Ecstasy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.11099433898925781, "target_z": -0.480468759152592, "ce": 6.340320587158203, "genuineness": 3.9299514293670654, "identity": 0.5616662502288818, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/2d5072b1ceffc9301fe2bf48.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-1-seed1701-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "d9d3bfb29d93ccfebedf4faccf8f3494cf057a140cda9fa8e471c02fd3477052", "task_id": "emo_Pleasure_Ecstasy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.1229187548160553, "target_z": -0.46093751830518404, "ce": 6.300607204437256, "genuineness": 4.174716949462891, "identity": 0.5626240372657776, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/08a5f8b5618f9142a4645201.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-1-seed1701-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "afef31c0ae2369e1f96cdd98161d9fca928cabf1edf0db9e46290c72610333e2", "task_id": "emo_Pleasure_Ecstasy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.23739321529865265, "target_z": -0.273437493898272, "ce": 6.41180419921875, "genuineness": 4.344170093536377, "identity": 0.5923956632614136, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/3a08007f57607d1d4c9b5f01.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-1-seed1701-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "37bf99fffa9c46bb567a3a0a9a16b67ab4f987bf4ec7cc118d2d74a928267826", "task_id": "emo_Pleasure_Ecstasy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.3357696831226349, "target_z": -0.11230469588987602, "ce": 6.427689552307129, "genuineness": 4.369274139404297, "identity": 0.4959375262260437, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/17ec38dd2be5cb1ccd70f149.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-1-seed1702-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "79f6ff2d73bef5b7fe1eb015bd80f13094a6bf9f0bac9123830accf29102e9de", "task_id": "emo_Pleasure_Ecstasy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.19208040833473206, "target_z": -0.347656253050864, "ce": 6.483288764953613, "genuineness": 4.607763767242432, "identity": 0.46364110708236694, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/7e80341f7b54160025c53ed1.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-1-seed1702-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "ec60b4e7034cd2f6718bb550b76457b382e6df99875b3d2515f39f74901fa596", "task_id": "emo_Pleasure_Ecstasy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.16107691824436188, "target_z": -0.398437493898272, "ce": 6.419747352600098, "genuineness": 4.469690799713135, "identity": 0.47836893796920776, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/3b38a0343b1a67e9f494c525.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-1-seed1702-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "99264f697531519cf2e853c0b23c78340cea8f871c536ac97b156f39d78808f7", "task_id": "emo_Pleasure_Ecstasy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.1264961063861847, "target_z": -0.45507810211851996, "ce": 6.483288764953613, "genuineness": 4.2751336097717285, "identity": 0.3917136490345001, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/6be4d6f9c53da83ec427b50d.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-de-1-seed1702-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "a05c14deb8eb96feeab289050ba039cacd33794e14c5a664c77e3b63e6e3933e", "task_id": "emo_Pleasure_Ecstasy-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.4532252550125122, "target_z": 0.08007815093234404, "ce": 6.515059471130371, "genuineness": 4.306513786315918, "identity": 0.5059515833854675, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/de/be484a05583f588053a4e543.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-0-seed1701-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "4dbbd5499910b8267102038ee84e94266998357cd77bfeac2b76afe4a26a6742", "task_id": "emo_Pleasure_Ecstasy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.11099433898925781, "target_z": -0.480468759152592, "ce": 6.213237762451172, "genuineness": 4.3881025314331055, "identity": 0.33558380603790283, "hypothesis": "The 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_Pleasure_Ecstasy/en/d25f3502128c906591f0d3e1.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-0-seed1701-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "7977e9892c56b3a5877298bd381dfc800a3ea4921c9faf4409c3fcfd44737864", "task_id": "emo_Pleasure_Ecstasy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.15392225980758667, "target_z": -0.410156253050864, "ce": 6.252951145172119, "genuineness": 4.162164688110352, "identity": 0.39852526783943176, "hypothesis": "The 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_Pleasure_Ecstasy/en/b1eb0202e9def7d3fba6c645.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-0-seed1701-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "31d818cbd8426e7c27db7e7e58a5d6758f3fcc5758ca936cfdc130f31a7f0c59", "task_id": "emo_Pleasure_Ecstasy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.07522109150886536, "target_z": -0.539062481694816, "ce": 6.284721851348877, "genuineness": 3.948779582977295, "identity": 0.45739495754241943, "hypothesis": "The 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_Pleasure_Ecstasy/en/b1de0fcdca06e7c95f9eaed3.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-0-seed1701-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "f7a49f940dffa6c5f530a2d7c201147180a901d0d15fef20630e70d0d8ac81a8", "task_id": "emo_Pleasure_Ecstasy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.3304036855697632, "target_z": -0.12109377135604803, "ce": 6.324435234069824, "genuineness": 4.099404335021973, "identity": 0.34804362058639526, "hypothesis": "The 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_Pleasure_Ecstasy/en/1bbc8a0a97a5c01ace97519c.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-0-seed1702-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "d81b9ad92037d7c11b6fcf68cbdd45431335a7eae6990402994208648fd36f1a", "task_id": "emo_Pleasure_Ecstasy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.31072840094566345, "target_z": -0.15332031631358, "ce": 6.268836498260498, "genuineness": 4.042920112609863, "identity": 0.2657695412635803, "hypothesis": "The 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_Pleasure_Ecstasy/en/13dd0ce5fdb7990c717dc559.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-0-seed1702-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "dfc1a79b2460878b6f1bbd00381ef441f45592549f9ed42cbb8847588312407d", "task_id": "emo_Pleasure_Ecstasy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.07045131921768188, "target_z": -0.546874987796544, "ce": 6.109982967376709, "genuineness": 3.936227321624756, "identity": 0.28390562534332275, "hypothesis": "The 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_Pleasure_Ecstasy/en/feac53a500eeb9cc43c89d70.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-0-seed1702-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "4f11d73a2e21ea04ac42d6338d8b6208dff618e3f3e03bb0b6261841cc5e5541", "task_id": "emo_Pleasure_Ecstasy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.10145479440689087, "target_z": -0.49609377135604804, "ce": 6.316492557525635, "genuineness": 4.287685871124268, "identity": 0.26946282386779785, "hypothesis": "The 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_Pleasure_Ecstasy/en/e3202a8ab8cf3352aea61a55.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-0-seed1702-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "63e025fde4dc8661238af00cd031c08f47fcc7c608d1c326ca1911fe9e044445", "task_id": "emo_Pleasure_Ecstasy-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.05614200234413147, "target_z": -0.570312506101728, "ce": 6.229123115539551, "genuineness": 4.143336772918701, "identity": 0.4306185245513916, "hypothesis": "The 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_Pleasure_Ecstasy/en/950752e0c70c71e56756fa02.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-1-seed1701-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "154039816b4df9947c70012130856f779e9217b7a322d1bbbb122021ace4bba3", "task_id": "emo_Pleasure_Ecstasy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.8169201016426086, "target_z": 0.67578126525432, "ce": 6.2767791748046875, "genuineness": 4.494794845581055, "identity": 0.5832399129867554, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/en/a8d21047f7d3ea608e67cc7a.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-1-seed1701-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "81a37f1ac7847de125a47250e3c0dbbf969752f21725ac5ee6d7075c0966b9e4", "task_id": "emo_Pleasure_Ecstasy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 1.0339446067810059, "target_z": 1.0312500732207361, "ce": 6.427689552307129, "genuineness": 4.582659721374512, "identity": 0.4677801728248596, "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_Pleasure_Ecstasy/en/7fbce07b62d3abc6074064e8.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-1-seed1701-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "e17b87d3e2d1e4e6b908639c7182edd48e59c308b561264674f3564bbb81a92d", "task_id": "emo_Pleasure_Ecstasy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 1.07687246799469, "target_z": 1.101562481694816, "ce": 6.3641486167907715, "genuineness": 4.21237325668335, "identity": 0.42005160450935364, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/en/f101513d601b13fff4012d80.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-1-seed1701-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "f93f23fe1602cacb853b0eecd8bff4c16eb1288a6778df2908a854f00b7de5c9", "task_id": "emo_Pleasure_Ecstasy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.7084078788757324, "target_z": 0.49804691008493607, "ce": 6.38797664642334, "genuineness": 4.394378662109375, "identity": 0.43886926770210266, "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_Pleasure_Ecstasy/en/b26278092bdd468af5c241fa.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-1-seed1702-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "c5ed9b8a3712edb3682dcf02c9e8ae329c4be2a6ff1a9518d22b2543d52d85aa", "task_id": "emo_Pleasure_Ecstasy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 1.072102665901184, "target_z": 1.0937499267792639, "ce": 6.268836498260498, "genuineness": 4.519899368286133, "identity": 0.4361274838447571, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/en/309f2d6d6868fb1047e260c0.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-1-seed1702-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "6098c1df09ee60faf43676b752b3c84bac24d8bba642934eedd9479627a3058a", "task_id": "emo_Pleasure_Ecstasy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.9313945770263672, "target_z": 0.8632813140681441, "ce": 6.356205940246582, "genuineness": 4.243753433227539, "identity": 0.388375848531723, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/en/c799f96ed486bc49e2bd3add.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-1-seed1702-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "0042570aeb2fa1fc1f1b4b8815e60cf13f26a680ba9a6bdc5bc900c9ad73583f", "task_id": "emo_Pleasure_Ecstasy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.9552433490753174, "target_z": 0.9023436981353119, "ce": 6.403861999511719, "genuineness": 4.362998008728027, "identity": 0.4153919219970703, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/en/1376da7c03dcf91fbe8e799b.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-en-1-seed1702-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "030c41ff32305c28d764e3bfccb5fb0940138fdf4f9486619a92572e8b12e74b", "task_id": "emo_Pleasure_Ecstasy-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.8884665966033936, "target_z": 0.7929687103387679, "ce": 6.356205940246582, "genuineness": 4.545003414154053, "identity": 0.5744743347167969, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/en/c3919258b6615af1bff1c937.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-0-seed1701-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "f5de6c1a413f6e87f8f632fe4e82b2a19690fd651b43a6d6d8d068c278c274b0", "task_id": "emo_Pleasure_Ecstasy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.6464008688926697, "target_z": 0.396484379576296, "ce": 6.173524379730225, "genuineness": 3.9550557136535645, "identity": 0.4948056936264038, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/c886b0dca1f3ff5c9805eba8.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-0-seed1701-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "11297f831390f569fc23c9e284da8352f06ba53dec81e69f1c887f6c4ddfe653", "task_id": "emo_Pleasure_Ecstasy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.5027115941047668, "target_z": 0.16113282241530802, "ce": 6.086154937744141, "genuineness": 3.911123275756836, "identity": 0.37470248341560364, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/fb3cbe644e31637f5bd5e10b.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-0-seed1701-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "60c25c5d2c9aff0d9cf9c11b61613c71cc9ec7e5d26f53369ce03ffc96395107", "task_id": "emo_Pleasure_Ecstasy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.47677597403526306, "target_z": 0.11865234794493801, "ce": 6.157639026641846, "genuineness": 4.344170093536377, "identity": 0.48624861240386963, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/7fbee2aeb7ba0d9491608d06.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-0-seed1701-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "77489f8d7514c8fbf7b1bd2eac7a28f0d722e32fa5cac64ac757252002b661a9", "task_id": "emo_Pleasure_Ecstasy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.4140236973762512, "target_z": 0.015869130137654983, "ce": 6.141753673553467, "genuineness": 4.218649387359619, "identity": 0.49845123291015625, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/595a7e071b5fc8dd8f037ee3.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-0-seed1702-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1702, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "6cbb79ffee0616c6075c22c16569a64640af242d73f03082356ccf67ce256b4f", "task_id": "emo_Pleasure_Ecstasy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.9242398738861084, "target_z": 0.851562481694816, "ce": 5.8875885009765625, "genuineness": 4.099404335021973, "identity": 0.5448303818702698, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/25b057b8e83f1a2e66a1dd4d.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-0-seed1702-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "1015a9c0ec7182540f31cf3db863a9c33bfe49966cbf55018b788b8bec91cbeb", "task_id": "emo_Pleasure_Ecstasy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.2695891559123993, "target_z": -0.22070311432197598, "ce": 6.062326908111572, "genuineness": 3.9048471450805664, "identity": 0.48943623900413513, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/105db79e1ec3687b184ea25b.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-0-seed1702-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "981fd6aeecec8094f35b6e9965ba2c012d40b5c6e51859be16bd1a2ab0a5e912", "task_id": "emo_Pleasure_Ecstasy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.13245829939842224, "target_z": -0.445312506101728, "ce": 5.967014789581299, "genuineness": 3.9927117824554443, "identity": 0.7823251485824585, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/86d86e91d0b3659893df0e23.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-0-seed1702-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "e97e328cf6a785915343e3c525a61fec8e3785df4078c55a3dfddd10ab546452", "task_id": "emo_Pleasure_Ecstasy-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.02990826964378357, "target_z": -0.61328126525432, "ce": 6.205295085906982, "genuineness": 4.306513786315918, "identity": 0.6067863702774048, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/da2d4b4974fb68e67aab8a8f.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-1-seed1701-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "09c6c41a62c9ac28bb80f7bdc5a53a05cca51fef6bc2cd77d4251c2e5016e2a9", "task_id": "emo_Pleasure_Ecstasy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.6690572500228882, "target_z": 0.43359372254222395, "ce": 6.308549880981445, "genuineness": 4.632867813110352, "identity": 0.7360814213752747, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/ad533af95d7fe9adaa669ffd.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-1-seed1701-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "1281d1ef474a5c1e8329b0c1aad9503cadce646e7369160ca4142633c3f5b55a", "task_id": "emo_Pleasure_Ecstasy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.4788627624511719, "target_z": 0.12207034072049204, "ce": 6.1894097328186035, "genuineness": 4.758388519287109, "identity": 0.5855173468589783, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/b1ce0a5f99cafc95201217ca.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-1-seed1701-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "386dddbeef11846cc0a1845639cacfdb71cbd15fa03f3d48b91ac59df5a2dd70", "task_id": "emo_Pleasure_Ecstasy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.46127423644065857, "target_z": 0.09326173972469003, "ce": 6.157639026641846, "genuineness": 4.545003414154053, "identity": 0.6879890561103821, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/2cf40930b0191bcdd0f92675.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-1-seed1701-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "d5bc9ff380926d27fefbcf944d796be827765d16b2b6bdf6c8dd1b6cc2551c62", "task_id": "emo_Pleasure_Ecstasy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.19208040833473206, "target_z": -0.347656253050864, "ce": 6.157639026641846, "genuineness": 4.482243061065674, "identity": 0.8116632699966431, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/d1336bc5806dceb59e30fd32.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-1-seed1702-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "b59de0783115b89bafc9e0e294527378d736b2c0bc5e4bc673ac4379875ee1b8", "task_id": "emo_Pleasure_Ecstasy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.5951258540153503, "target_z": 0.3125, "ce": 6.268836498260498, "genuineness": 4.419482707977295, "identity": 0.5572181940078735, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/64a91982faf08dab2053eb4d.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-1-seed1702-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "1763faf4ed68cfaed9f1f1263c5ea1fb93e650078a6d1cc1f3a3098bcea8cb5b", "task_id": "emo_Pleasure_Ecstasy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.32623016834259033, "target_z": -0.12792965927950795, "ce": 6.078212261199951, "genuineness": 4.6956281661987305, "identity": 0.6680688261985779, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/2e98ae11d412614fdea75bec.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-1-seed1702-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "4e8410efd1cc14d85ec8294c460a6c18a6be86958f56ae7da42dd257dcf0ed6c", "task_id": "emo_Pleasure_Ecstasy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.339645117521286, "target_z": -0.10595704383481402, "ce": 6.117925643920898, "genuineness": 4.507347106933594, "identity": 0.6592110395431519, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/412436b3292068bc34ebdeb6.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-es-1-seed1702-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "1d9b069295abb03c44f84a316ce64dd442cfd4b3b57cde43c29ff554dfa14a35", "task_id": "emo_Pleasure_Ecstasy-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.6714421510696411, "target_z": 0.4375, "ce": 6.1894097328186035, "genuineness": 4.545003414154053, "identity": 0.5603201389312744, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/es/41fa0283dca4c64ebb5740c5.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-0-seed1701-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "d9e60555c45e671e1f323bd9342c4f36bad7e50847564cf5ab20f5bf2c9c9c33", "task_id": "emo_Pleasure_Ecstasy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.208774596452713, "target_z": -0.320312506101728, "ce": 6.1020402908325195, "genuineness": 4.632867813110352, "identity": 0.792919397354126, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/e1f0aee41cde288ff9f0106c.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-0-seed1701-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "9e89c409f7c22fba607f27a491d9c95734e59ab2a0f66e7fe7254971074132da", "task_id": "emo_Pleasure_Ecstasy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.2785324454307556, "target_z": -0.20605472029678806, "ce": 5.998785495758057, "genuineness": 4.519899368286133, "identity": 0.6966924667358398, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/38baeee7d238a808084196f9.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-0-seed1701-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "1d2373deb8ff2e55f595d924a0403e164846ab00b4c9606d4b9603a3e8bf9f8a", "task_id": "emo_Pleasure_Ecstasy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.1038396954536438, "target_z": -0.492187493898272, "ce": 6.09409761428833, "genuineness": 4.375550270080566, "identity": 0.7345402240753174, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/7be4587d85a1462c4979b221.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-0-seed1701-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "c159a07544a9195d6890a310ed09adb43548fa9340ab2e56f491d7e410f6383e", "task_id": "emo_Pleasure_Ecstasy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.11457166075706482, "target_z": -0.47460939177975203, "ce": 6.070269584655762, "genuineness": 4.406930446624756, "identity": 0.7853295207023621, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/aefcfcaa063cbd8055541068.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-0-seed1702-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "9c464da8f0f264328643f068164c2bfeac46e92de5f813bfd0e587b75f468e0f", "task_id": "emo_Pleasure_Ecstasy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.23381587862968445, "target_z": -0.279296885678024, "ce": 6.141753673553467, "genuineness": 4.545003414154053, "identity": 0.7896728515625, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/2063f45622a5f1eda9c32db9.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-0-seed1702-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "d059e5f099e12bf1476fdf33f8492cd905c4c9aa7e15b6ee21c7e06686344fe9", "task_id": "emo_Pleasure_Ecstasy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.3551468849182129, "target_z": -0.08056638680074198, "ce": 6.300607204437256, "genuineness": 4.65797233581543, "identity": 0.6261361837387085, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/ea5e368239e436ba97075682.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-0-seed1702-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "43e2d47174fa6ee4db5cf447e1f7217805b8d6ecb1282200018b4a4507aaa4c6", "task_id": "emo_Pleasure_Ecstasy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.8407689332962036, "target_z": 0.714843746949136, "ce": 6.197352409362793, "genuineness": 4.482243061065674, "identity": 0.8035388588905334, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/995578f62a47f38b766dca35.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-0-seed1702-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "6fcfb500d419ee06147efad99c6caaf04cf8176dca9ab287ff5e7107cc13cc49", "task_id": "emo_Pleasure_Ecstasy-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.10980188846588135, "target_z": -0.48242189788148004, "ce": 6.109982967376709, "genuineness": 4.293961524963379, "identity": 0.5515905618667603, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/9e6b260bc5c729f3b0493513.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-1-seed1701-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "41f615d8779646259053ab58bb87ce93c848ea88a393e944fa26d03bc4ffd2d6", "task_id": "emo_Pleasure_Ecstasy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.8121503591537476, "target_z": 0.6679688079664161, "ce": 6.205295085906982, "genuineness": 4.6956281661987305, "identity": 0.801923394203186, "hypothesis": "J'ai trouvé la petite boîte, elle était près de la vieille fenêtre, nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/3f6d7e6075d765cc95b0f726.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-1-seed1701-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "b1b29253439c272407a8d15c4aa19212cab3be5dd6130da5113292b773e9fc6e", "task_id": "emo_Pleasure_Ecstasy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.7382189035415649, "target_z": 0.546874987796544, "ce": 6.229123115539551, "genuineness": 4.6956281661987305, "identity": 0.7127519249916077, "hypothesis": "J'ai trouvé la petite boîte elle était près de la vieille fenêtre nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/8dd44288ae4bbd769d45b64f.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-1-seed1701-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "3fd4e09e729d948b41b6bbd94bf255427ab676cac098214ccd2a6d1b76d4535f", "task_id": "emo_Pleasure_Ecstasy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.4410026967525482, "target_z": 0.060058576588889974, "ce": 6.348263263702393, "genuineness": 4.494794845581055, "identity": 0.586932897567749, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/9797f8157cd99067ec63c4aa.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-1-seed1701-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "d4875577e5ea7559a796d7702ccb47f61329073d5c93c9cef764a33b158e54af", "task_id": "emo_Pleasure_Ecstasy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.6130124926567078, "target_z": 0.341796885678024, "ce": 6.23706579208374, "genuineness": 4.444586753845215, "identity": 0.686998724937439, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/b57913991e15e086db618a6b.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-1-seed1702-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "d6d81fbcba7f47666d04d921bae8c50e6c49981ef3a9d1fa844a0b0897b3cf73", "task_id": "emo_Pleasure_Ecstasy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.6308991312980652, "target_z": 0.37109377135604804, "ce": 6.24500846862793, "genuineness": 4.582659721374512, "identity": 0.7435486316680908, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/7028ac9a09deeaebcb3bc6f5.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-1-seed1702-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "0a75989294cef19fb3c095efc73c451079b441bd8663b0ffb40e66ba6c565255", "task_id": "emo_Pleasure_Ecstasy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.5170208811759949, "target_z": 0.18457029190666796, "ce": 6.308549880981445, "genuineness": 4.281409740447998, "identity": 0.6079337000846863, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/297a6a51fcc6cd1a55ba04a7.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-1-seed1702-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "14b8daa02cf3bb5a51268cf3296ac51873fd5515b7c5cbd56269f822638b59aa", "task_id": "emo_Pleasure_Ecstasy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.379293829202652, "target_z": -0.04101562042370399, "ce": 6.1894097328186035, "genuineness": 4.758388519287109, "identity": 0.8364732265472412, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/adc81d9a35d98168c8483c90.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-fr-1-seed1702-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "699e687cf82730dac165613fe3ddf2e26f3b409fcc4c41871831b2f740d68945", "task_id": "emo_Pleasure_Ecstasy-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.4666402041912079, "target_z": 0.10205076637703797, "ce": 6.332377910614014, "genuineness": 4.250029563903809, "identity": 0.638329029083252, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/fr/29e2f29c6942dd30852b7ced.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-0-seed1701-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "4ea5f1d3592a5d8a7b848d403fa0f074e379d02170f01627564038b2d63ae925", "task_id": "emo_Pleasure_Ecstasy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.09430015087127686, "target_z": -0.507812506101728, "ce": 6.197352409362793, "genuineness": 4.168440818786621, "identity": 0.8017899394035339, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/028d948256fed9ba4314de0c.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-0-seed1701-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "7178b2bca148797f9eba96f92a92e8386287ad42856dcf2b654f35f677dcd7f0", "task_id": "emo_Pleasure_Ecstasy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": -0.008249878883361816, "target_z": -0.67578126525432, "ce": 6.09409761428833, "genuineness": 4.118232727050781, "identity": 0.7562036514282227, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/924a0c120d5868a3e6ec255f.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-0-seed1701-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "57fa780c354eccb5d64653cc5b7dd937442a050a092f1f24ef947d0124bfc021", "task_id": "emo_Pleasure_Ecstasy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.0322931706905365, "target_z": -0.609374987796544, "ce": 6.24500846862793, "genuineness": 4.400654315948486, "identity": 0.7273849248886108, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/1c066d6a54adeb53c30ea97e.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-0-seed1701-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "30cf407959cb628968b5e187620286620c65989451c3562172ce1f71a87ef650", "task_id": "emo_Pleasure_Ecstasy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.048987358808517456, "target_z": -0.582031240847408, "ce": 6.157639026641846, "genuineness": 4.20609712600708, "identity": 0.506805419921875, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/410da00251dd13e7384aa387.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-0-seed1702-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "fee047a08932e659093f2816345c443d2b6d91b95823616a551539bf7f978a94", "task_id": "emo_Pleasure_Ecstasy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.013214081525802612, "target_z": -0.640625012203456, "ce": 6.125868320465088, "genuineness": 4.293961524963379, "identity": 0.6823629140853882, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/75d70fd7f01b229cfe9ff3ce.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-0-seed1702-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "78b9148d1cf5dfcaa60decadf291cf7dc1cd06f20fad671da67c78393c8b3ab1", "task_id": "emo_Pleasure_Ecstasy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.044217586517333984, "target_z": -0.589843746949136, "ce": 6.062326908111572, "genuineness": 4.124508857727051, "identity": 0.7047820687294006, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/78d50ff93101e1378aca514d.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-0-seed1702-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "0c3d1aaf947292c9891e8893bd12d2a50bb6f71dbfbe1dbcda5f6e718369796b", "task_id": "emo_Pleasure_Ecstasy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.046602457761764526, "target_z": -0.585937518305184, "ce": 5.998785495758057, "genuineness": 4.331617832183838, "identity": 0.40494388341903687, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/a843bf30de6bed739e2699ba.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-0-seed1702-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "a541b6bc9f6ea689c5c6fe11e75889a502df768ddeb32e6d358291beff41a32b", "task_id": "emo_Pleasure_Ecstasy-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.027523398399353027, "target_z": -0.617187493898272, "ce": 6.070269584655762, "genuineness": 4.3504462242126465, "identity": 0.6613437533378601, "hypothesis": "De deur staat nog open. Het nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.15789473684210525, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/6dbc93ecd2f89cb340e766c7.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-1-seed1701-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "39d5e8ed6e2af8961ad8b4da58f62814a5e85a672612ba75f6ef1de0a0f84cde", "task_id": "emo_Pleasure_Ecstasy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.23977810144424438, "target_z": -0.269531240847408, "ce": 6.117925643920898, "genuineness": 4.21237325668335, "identity": 0.48000216484069824, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/560b9d99d5f90541ee389188.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-1-seed1701-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "2259558848a6b1ac4720be1ad7429d923327c4b42da61d7a10c9fd8fef92c3d0", "task_id": "emo_Pleasure_Ecstasy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.051372230052948, "target_z": -0.578125012203456, "ce": 6.221180438995361, "genuineness": 4.3127899169921875, "identity": 0.6744732856750488, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/3dad04e171df60c3a0f27a7d.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-1-seed1701-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "8235c3737dd52e5326af9782047a316e971f315bbffe35a3c0a06c5751b00bc1", "task_id": "emo_Pleasure_Ecstasy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.05614200234413147, "target_z": -0.570312506101728, "ce": 6.197352409362793, "genuineness": 4.287685871124268, "identity": 0.7058682441711426, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/a4abb4c5c8edb459b38e81ff.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-1-seed1701-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "1ef82a37b26976f378d53607b8093632b92c9742538919c0e78c90050311bee3", "task_id": "emo_Pleasure_Ecstasy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.05614200234413147, "target_z": -0.570312506101728, "ce": 6.149696350097656, "genuineness": 4.118232727050781, "identity": 0.63774573802948, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/76e1cad867d55a1edd4d7ae7.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-1-seed1702-scale0.0", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "ba0da5677374a6093f148c21358e70c51ab79acc8d6799be4ccf208a4936d7f3", "task_id": "emo_Pleasure_Ecstasy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.02990826964378357, "target_z": -0.61328126525432, "ce": 6.157639026641846, "genuineness": 4.406930446624756, "identity": 0.8437960743904114, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/b1cadda85590bbdc713cc2fb.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-1-seed1702-scale0.5", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "202f5766323af144552b6b493444948adff19b1499a9c62e267632fcc1d229e0", "task_id": "emo_Pleasure_Ecstasy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.07999083399772644, "target_z": -0.531250024406912, "ce": 6.109982967376709, "genuineness": 4.256305694580078, "identity": 0.7039979696273804, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/4dd56d16345648a266039162.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-1-seed1702-scale0.75", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "f98daa8434bda9ae232e11b4741632ab78acc44e4a191ca8dc6dca9e921aede8", "task_id": "emo_Pleasure_Ecstasy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.046602457761764526, "target_z": -0.585937518305184, "ce": 6.173524379730225, "genuineness": 4.18726921081543, "identity": 0.6485998630523682, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/ef708004d0cbce16b76771e0.mp3" }, { "key": "original-emo_Pleasure_Ecstasy-nl-1-seed1702-scale1.0", "bucket": "emo_Pleasure_Ecstasy", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "e338f630f94c8793f1e5093df8c01a1862889a533d60be0183bf02017e088a1d", "mp3_sha256": "e6747f917224ffaeb64775c13e67440ebaeb2d65ce140be9a2b5550cc1c2bdc3", "task_id": "emo_Pleasure_Ecstasy-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Pleasure Ecstasy. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Pleasure Ecstasy. 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 Pleasure Ecstasy. 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 Pleasure Ecstasy. 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": 0.06329664587974548, "target_z": -0.558593771356048, "ce": 6.229123115539551, "genuineness": 4.18099308013916, "identity": 0.6509315967559814, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Pleasure_Ecstasy/nl/2bb7ba024500bba9d576e547.mp3" } ], "source_standard_audio_unchanged": true }