{ "complete": true, "report": { "bucket": "emo_Relief", "label": "Intense Relief", "definition": { "id": "emo_Relief", "category": "emotion", "head": "emo_Relief", "pole": "high", "label": "Intense Relief", "floor": 3.0 }, "recipe_status": "direct_manual_recipe", "manual_provenance": [ { "id": "rank4/emotion_relief/full-v2-sealed/sealed-selected", "mission": "emotion_relief", "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": 6.393139276504517, "genuineness": 4.4414486718177795, "wer": 0.012688153879686137, "identity": 0.6012727105617524, "voiceclap": -0.029205971956253053, "fitness": 0.6529053599672978, "steering_v2": 0.6311473234325445, "raw_target": 0.714127394258976, "target_cdf": 0.6311473234325445, "family_hit_all": null, "nominal_hit_all": null, "n": 100, "valid_fraction": 1, "by_arm": { "reference": { "n": 50, "ce": 6.3976665878295895, "genuineness": 4.428896603584289, "wer": 0.012742589363557105, "identity": 0.6012727105617524, "fitness": 0.6549186062006743, "steering_v2": 0.6360305464189842 }, "none": { "n": 50, "ce": 6.388611965179443, "genuineness": 4.45400074005127, "wer": 0.01263371839581517, "identity": null, "fitness": 0.6508921137339213, "steering_v2": 0.6262641004461049 } } } } ], "selected_wording": { "id": "manual-c17f294b7963", "general": "Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.", "inline": [ "Project the sound from a relaxed throat space", "Introduce a gentle upward inflection on the key words", "Ensure the final word carries a lingering, warm resonance" ], "cfg": 3, "recipe": "P01", "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": 5.0 }, "n": 20, "target_z": 0.8486328157360683, "target_raw": 0.9622198313474655, "ce": 6.181467032432556, "genuineness": 4.265405762195587, "identity": 0.542939305305481, "wer": 0.050561790505675955, "valid_fraction": 0.9, "identity_delta": -0.04243461787700653, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "manual_adapter": { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 0.7958740308395891, "target_raw": 0.9253993906080723, "ce": 6.125868344306946, "genuineness": 4.190407121181488, "identity": 0.5496146827936172, "wer": 0.048998968008255935, "valid_fraction": 0.9, "identity_delta": -0.03575924038887024, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, "grid": [ { "config": { "scale": 0.0, "cfg": 5.0 }, "n": 20, "target_z": 0.8486328157360683, "target_raw": 0.9622198313474655, "ce": 6.181467032432556, "genuineness": 4.265405762195587, "identity": 0.542939305305481, "wer": 0.050561790505675955, "valid_fraction": 0.9, "identity_delta": -0.04243461787700653, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.5 }, "n": 20, "target_z": 0.5883544789554838, "target_raw": 0.7805711619555951, "ce": 6.218797636032105, "genuineness": 4.291451346874237, "identity": 0.5557296097278595, "wer": 0.005263157894736842, "valid_fraction": 1, "identity_delta": -0.02964431345462799, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.0 }, "n": 20, "target_z": 0.5836914105369564, "target_raw": 0.7773167990148068, "ce": 6.190601110458374, "genuineness": 4.273564648628235, "identity": 0.550184516608715, "wer": 0.003333333333333333, "valid_fraction": 1, "identity_delta": -0.03518940657377243, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 2.5 }, "n": 20, "target_z": 0.5419067365818971, "target_raw": 0.7481552079319954, "ce": 6.196161007881164, "genuineness": 4.306043136119842, "identity": 0.5654786452651024, "wer": 0.012777777777777777, "valid_fraction": 1, "identity_delta": -0.0198952779173851, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.0 }, "n": 20, "target_z": 0.37894286187554266, "target_raw": 0.6344224579632283, "ce": 6.21284065246582, "genuineness": 4.371784615516662, "identity": 0.5495735302567482, "wer": 0.023684210526315787, "valid_fraction": 0.95, "identity_delta": -0.03580039292573929, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 4.0 }, "n": 20, "target_z": 0.7660888528211918, "target_raw": 0.9046122670173645, "ce": 6.175907182693481, "genuineness": 4.248774290084839, "identity": 0.5177587099373341, "wer": 0.07206398348813209, "valid_fraction": 0.9, "identity_delta": -0.06761521324515343, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 3.0 }, "n": 20, "target_z": 0.6086669813575138, "target_raw": 0.7947472900152206, "ce": 6.194373893737793, "genuineness": 4.267916202545166, "identity": 0.5326111912727356, "wer": 0.024613003095975233, "valid_fraction": 0.9, "identity_delta": -0.05276273190975189, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.0, "cfg": 1.25 }, "n": 20, "target_z": 0.3732665915582116, "target_raw": 0.6304609797894954, "ce": 6.2164147853851315, "genuineness": 4.330362796783447, "identity": 0.5292566820979119, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.05611724108457565, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 4.0 }, "n": 20, "target_z": 0.7958740308395891, "target_raw": 0.9253993906080723, "ce": 6.125868344306946, "genuineness": 4.190407121181488, "identity": 0.5496146827936172, "wer": 0.048998968008255935, "valid_fraction": 0.9, "identity_delta": -0.03575924038887024, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 3.0 }, "n": 20, "target_z": 0.7784667987349052, "target_raw": 0.9132508553564549, "ce": 6.1520792007446286, "genuineness": 4.28674430847168, "identity": 0.5521195933222771, "wer": 0.019122807017543857, "valid_fraction": 0.95, "identity_delta": -0.033254329860210416, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.5 }, "n": 20, "target_z": 0.569189456202601, "target_raw": 0.7671958617866039, "ce": 6.198940896987915, "genuineness": 4.289568555355072, "identity": 0.5550970122218132, "wer": 0.0059649122807017545, "valid_fraction": 1, "identity_delta": -0.030276910960674287, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.0 }, "n": 20, "target_z": 0.566369645864332, "target_raw": 0.7652279116213322, "ce": 6.177098560333252, "genuineness": 4.29709974527359, "identity": 0.5425364688038826, "wer": 0.008388157894736842, "valid_fraction": 1, "identity_delta": -0.04283745437860489, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 2.5 }, "n": 20, "target_z": 0.5309081836502078, "target_raw": 0.7404793001711368, "ce": 6.179481410980225, "genuineness": 4.3523289322853085, "identity": 0.538614559173584, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.0467593640089035, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.0 }, "n": 20, "target_z": 0.4730895929026652, "target_raw": 0.700127612799406, "ce": 6.20728075504303, "genuineness": 4.28454772233963, "identity": 0.5600526601076126, "wer": 0.005555555555555555, "valid_fraction": 1, "identity_delta": -0.025321263074874877, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.25 }, "n": 20, "target_z": 0.45413818535148553, "target_raw": 0.6869013950228691, "ce": 6.13281819820404, "genuineness": 4.268230056762695, "identity": 0.5366040274500847, "wer": 0.013333333333333332, "valid_fraction": 0.95, "identity_delta": -0.0487698957324028, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.5 }, "n": 20, "target_z": 0.43260496059987463, "target_raw": 0.6718733228743077, "ce": 6.1983452320098875, "genuineness": 4.300865387916565, "identity": 0.5598021313548088, "wer": 0.031578947368421054, "valid_fraction": 0.95, "identity_delta": -0.02557179182767868, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.25 }, "n": 20, "target_z": 0.3956787041609395, "target_raw": 0.6461024291813373, "ce": 6.187026929855347, "genuineness": 4.319379711151123, "identity": 0.5757239267230034, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.009649996459484101, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.25 }, "n": 20, "target_z": 0.3654296920038064, "target_raw": 0.6249915950000287, "ce": 6.2303145170211796, "genuineness": 4.347308051586151, "identity": 0.5363348912447691, "wer": 0.005409356725146199, "valid_fraction": 1, "identity_delta": -0.04903903193771839, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 5.0 }, "n": 20, "target_z": 0.9749023281201239, "target_raw": 1.0503435268998147, "ce": 6.05617139339447, "genuineness": 4.22461154460907, "identity": 0.45973998717963693, "wer": 0.03703624871001032, "valid_fraction": 0.9, "identity_delta": -0.12563393600285053, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 5.0 }, "n": 20, "target_z": 0.9416015762783113, "target_raw": 1.027102878689766, "ce": 6.071063899993897, "genuineness": 4.154006028175354, "identity": 0.44426784962415694, "wer": 0.033292053663570687, "valid_fraction": 0.95, "identity_delta": -0.14110607355833055, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 5.0 }, "n": 20, "target_z": 0.8883300796679706, "target_raw": 0.9899246156215668, "ce": 6.112167239189148, "genuineness": 4.2023315787315365, "identity": 0.5227461293339729, "wer": 0.1024438854489164, "valid_fraction": 0.75, "identity_delta": -0.06262779384851455, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 4.0 }, "n": 20, "target_z": 0.8220458873573023, "target_raw": 0.9436647713184356, "ce": 6.099260377883911, "genuineness": 4.257560682296753, "identity": 0.520968048274517, "wer": 0.07154605263157894, "valid_fraction": 0.9, "identity_delta": -0.06440587490797042, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 4.0 }, "n": 20, "target_z": 0.7747802676284238, "target_raw": 0.910678019374609, "ce": 6.135002446174622, "genuineness": 4.229004716873169, "identity": 0.5212975442409515, "wer": 0.060526315789473685, "valid_fraction": 0.9, "identity_delta": -0.06407637894153595, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 3.0 }, "n": 20, "target_z": 0.7557861220909388, "target_raw": 0.8974219746887684, "ce": 6.1707444190979, "genuineness": 4.275133633613587, "identity": 0.5272096492350101, "wer": 0.022063983488132093, "valid_fraction": 0.95, "identity_delta": -0.05816427394747734, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 3.0 }, "n": 20, "target_z": 0.7045166097068831, "target_raw": 0.8616408996284008, "ce": 6.197352409362793, "genuineness": 4.283920121192932, "identity": 0.4851813606917858, "wer": 0.027820562435500514, "valid_fraction": 0.95, "identity_delta": -0.10019256249070167, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.5 }, "n": 20, "target_z": 0.5766113458149505, "target_raw": 0.7723756104707717, "ce": 6.191792511940003, "genuineness": 4.315927886962891, "identity": 0.5264580816030502, "wer": 0.03978328173374613, "valid_fraction": 0.9, "identity_delta": -0.05891584157943726, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 2.0 }, "n": 20, "target_z": 0.5574096638131546, "target_raw": 0.7589747257530689, "ce": 6.196955251693725, "genuineness": 4.306200003623962, "identity": 0.5116626217961311, "wer": 0.014353070175438597, "valid_fraction": 1, "identity_delta": -0.07371130138635636, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 2.0 }, "n": 20, "target_z": 0.5448364264505656, "target_raw": 0.750199843198061, "ce": 6.167170262336731, "genuineness": 4.224611592292786, "identity": 0.5259149610996247, "wer": 0.0029411764705882353, "valid_fraction": 1, "identity_delta": -0.05945896208286285, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.5 }, "n": 20, "target_z": 0.4888915910244272, "target_raw": 0.7111558526754379, "ce": 6.166177415847779, "genuineness": 4.35734977722168, "identity": 0.5204569861292839, "wer": 0.0029411764705882353, "valid_fraction": 1, "identity_delta": -0.06491693705320359, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.5, "cfg": 1.0 }, "n": 20, "target_z": 0.4293823170105747, "target_raw": 0.6696242347359658, "ce": 6.203309440612793, "genuineness": 4.340404450893402, "identity": 0.5000287607312203, "wer": 0.0027777777777777775, "valid_fraction": 1, "identity_delta": -0.08534516245126725, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 1.0, "cfg": 1.5 }, "n": 20, "target_z": 0.418017572995665, "target_raw": 0.6616927616298198, "ce": 6.180275654792785, "genuineness": 4.2939617395401, "identity": 0.5264208301901817, "wer": 0.008596491228070175, "valid_fraction": 1, "identity_delta": -0.05895309299230576, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" }, { "config": { "scale": 0.75, "cfg": 1.0 }, "n": 20, "target_z": 0.3615966808343025, "target_raw": 0.6223165303468704, "ce": 6.184842681884765, "genuineness": 4.304003429412842, "identity": 0.5329971104860306, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.05237681269645691, "identity_pairs": 20, "gates_pass": false, "gate_scope": "development_provisional_20_pairs" } ], "development_standard": [ { "scale": 0.0, "n": 20, "target_z": 0.07894896943729554, "target_raw": 0.4250562384724617, "ce": 6.188218307495117, "genuineness": 4.431407046318054, "identity": 0.5853739231824875, "wer": 0.005409356725146199, "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": 0.19444579871492032, "target_raw": 0.5056616611778736, "ce": 6.175907135009766, "genuineness": 4.358604967594147, "identity": 0.5806466147303582, "wer": 0.0, "valid_fraction": 1, "identity_delta": -0.004727308452129364, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 0.75, "n": 20, "target_z": 0.1849365086875342, "target_raw": 0.49902511239051817, "ce": 6.194572472572327, "genuineness": 4.35389791727066, "identity": 0.5678380310535431, "wer": 0.023684210526315787, "valid_fraction": 0.95, "identity_delta": -0.017535892128944398, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" }, { "scale": 1.0, "n": 20, "target_z": 0.05029296973416509, "target_raw": 0.40505717024207116, "ce": 6.1306339502334595, "genuineness": 4.309024238586426, "identity": 0.5506714940071106, "wer": 0.002631578947368421, "valid_fraction": 1, "identity_delta": -0.034702429175376893, "identity_pairs": 20, "gates_pass": true, "gate_scope": "development_provisional_20_pairs" } ] }, "heldout": { "standard": { "n": 50, "target_z": -0.02017578290806797, "target_raw": 0.35587691456079484, "ce": 6.244214172363281, "genuineness": 4.4011565208435055, "identity": 0.5936945807933808, "wer": 0.007323546019198193, "valid_fraction": 1, "identity_delta": 0.0, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "manual": { "n": 50, "target_z": 0.4874121155919209, "target_raw": 0.7101233243942261, "ce": 6.222292404174805, "genuineness": 4.416846647262573, "identity": 0.5549879938364028, "wer": 0.06515222344398545, "valid_fraction": 0.92, "identity_delta": -0.038706586956977845, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "adapter": { "n": 50, "target_z": 0.3099951143776253, "target_raw": 0.5863037142157554, "ce": 6.253745384216309, "genuineness": 4.40165855884552, "identity": 0.5622172182798386, "wer": 0.04844760616957413, "valid_fraction": 0.92, "identity_delta": -0.031477362513542176, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" }, "matched_no_adapter": { "n": 50, "target_z": 0.32054687242449, "target_raw": 0.5936678031086922, "ce": 6.2512036895751955, "genuineness": 4.393374238014221, "identity": 0.5607603266835213, "wer": 0.03784679089026915, "valid_fraction": 0.94, "identity_delta": -0.032934254109859465, "identity_pairs": 50, "gates_pass": true, "gate_scope": "heldout_50_reference_pairs" } }, "adapter_vs_matched_cfg": { "n": 50, "delta_z": -0.010551758046864737, "ci95_z": [ -0.0899609414967111, 0.08083496699845569 ], "language_deltas": { "en": -0.010839842799196435, "de": -0.11855469787543536, "fr": -0.1009277344667442, "nl": 0.01379394263106715, "es": 0.16376954227598517 }, "languages_improved": 2, "clear_gain": false, "delta_ce": 0.002541694641113281, "delta_genuineness": 0.008284320831298828, "delta_wer": 0.010600815279304981, "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": -0.1774170012142956, "ci95_z": [ -0.24404785919978794, -0.10930665285033217 ], "language_deltas": { "en": -0.217382831749602, "de": -0.10444337127672533, "fr": -0.2951171831963628, "nl": -0.19523926610701003, "es": -0.07490235374177782 }, "languages_improved": 0, "clear_gain": false, "delta_ce": 0.0314529800415039, "delta_genuineness": -0.015188088417053222, "delta_wer": -0.016704617274411325, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "manual_vs_standard": { "n": 50, "delta_z": 0.5075878984999889, "ci95_z": [ 0.4101464871089773, 0.6399804767267414 ], "language_deltas": { "en": 0.5478027467437867, "de": 0.3977050748639106, "fr": 0.75146485400867, "nl": 0.4143554689334884, "es": 0.42661134795008837 }, "languages_improved": 5, "clear_gain": true, "delta_ce": -0.021921768188476562, "delta_genuineness": 0.015690126419067384, "delta_wer": 0.05782867742478726, "note": "Exploratory language-cluster bootstrap; five voices, one fixed reference voice per language. No familywise claim across72targets." }, "route": { "adapter": false, "scale": 0.0, "cfg": 5.0, "reason": "Use manual-only configuration; no clear qualifying incremental adapter gain" }, "reference_only": true, "updated": 1793025400.7482877, "example": { "text": "De weg gaat linksaf na de brug. Loop verder... tot aan het kleine houten hek. Ik wacht aan de andere kant.", "sentences": [ "De weg gaat linksaf na de brug.", "Loop verder... tot aan het kleine houten hek.", "Ik wacht aan de andere kant." ], "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Ensure the final word carries a lingering, warm resonance) [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.", "language": "nl", "seed": 1702, "scale": 0.0, "cfg": 5.0, "frames": 128, "reference": true } }, "rows": [ { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "003def6a63a077abac8c8908889b83749cdc9a62d338603d58e0ec9b0749c514", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ddf982b72f39e35c9e16473141c16fd944dbf52a82e90a16e585000824fb2316", "generation_seconds_batch": 28.998471656115726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2150728702545166, "target_z": 1.2109375253547616, "ce": 6.332377910614014, "genuineness": 4.507347106933594, "identity": 0.4905756413936615, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/003def6a63a077abac8c8908889b83749cdc9a62d338603d58e0ec9b0749c514.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": "004a830638108285363db1406185b4247f8eab2a13f4181fe0b09f98928b12d2", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5ed8c4def3c37caff50d2dedf2e6c58c6952436acbc17498d311b1a5b883cc32", "generation_seconds_batch": 19.680780119961128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28578686714172363, "target_z": -0.12060548067674645, "ce": 6.213237762451172, "genuineness": 4.419482707977295, "identity": 0.7219946980476379, "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_Relief/004a830638108285363db1406185b4247f8eab2a13f4181fe0b09f98928b12d2.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "00c0ddf3ca35204a686913f1b1df6135909da16b207d02f4b4e4dabbaa9c5c37", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f774da9141e632b94fc31537b3eb14d0f8e57b549a7b09456bcb834f84e88f33", "generation_seconds_batch": 20.92794738104567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.70391446352005, "target_z": 0.4785156453505324, "ce": 6.133810997009277, "genuineness": 3.8295347690582275, "identity": 0.38271939754486084, "hypothesis": "The 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_Relief/00c0ddf3ca35204a686913f1b1df6135909da16b207d02f4b4e4dabbaa9c5c37.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "012da9f5c157d04483c41304b101c31e91c3bd0a81c0768825281d67ef4929a1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "03abf60e26597a0ad7bfa7a9358e36d5a910a68693986b85142014717d3844a2", "generation_seconds_batch": 21.590063824900426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2363748997449875, "target_z": -0.191406245329386, "ce": 6.221180438995361, "genuineness": 4.306513786315918, "identity": 0.4789426922798157, "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_Relief/012da9f5c157d04483c41304b101c31e91c3bd0a81c0768825281d67ef4929a1.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "01437c06d18092353a3eedf2c4067cc5859f37c16c624149477e9a6e4aa60863", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7214e8380c70b09e81a053cedafc7827bb6c68a6ce347855fe6ad213d883ce27", "generation_seconds_batch": 28.10063522204291, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36399412155151367, "target_z": -0.008544906987417888, "ce": 6.078212261199951, "genuineness": 3.6475296020507812, "identity": 0.24044999480247498, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/01437c06d18092353a3eedf2c4067cc5859f37c16c624149477e9a6e4aa60863.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "017ed5984c521f79a8ca02558ad397737a9ece97a69bbfaa03712d2999f875b7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6a086abdb7feb4146891403571fd052253143456e8a4d9ecd8bfbed193fba070", "generation_seconds_batch": 29.40030817000661, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1060256958007812, "target_z": 1.0546874559627823, "ce": 6.09409761428833, "genuineness": 4.055472373962402, "identity": 0.38970381021499634, "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_Relief/017ed5984c521f79a8ca02558ad397737a9ece97a69bbfaa03712d2999f875b7.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "018a7d9556214524dbbccdbab2c7f07c3ba8c9cd4f5c6baa83a7ff14b579f008", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a6d6852913966ce95d0e93555d60d0790f87d3882972988ecaeb6a5dcd67cc19", "generation_seconds_batch": 17.10378360399045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38239580392837524, "target_z": 0.017822251654859924, "ce": 6.38003396987915, "genuineness": 4.306513786315918, "identity": 0.5865776538848877, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/018a7d9556214524dbbccdbab2c7f07c3ba8c9cd4f5c6baa83a7ff14b579f008.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "0b816acb08f89edb64aed4a79bb9dd38ab527fada66255b3e0d06316c587b6d8", "generation_seconds_batch": 16.564378419076093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5716947913169861, "target_z": 0.2890624746452383, "ce": 6.046441555023193, "genuineness": 4.331617832183838, "identity": 0.5162787437438965, "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_Relief/01f5d5f22d9b51f4e674eec92be80d0710e62f5704093e3409bc811236eec3e5.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "020f1687f57ccd3aa6868621bc69e7953a7c6ad5450e3a089933e5e67bf118e7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "492543d54cf7c53cb519048a4eacccb5c8d38a96e53a223af2606cf5454f1223", "generation_seconds_batch": 23.676856391015463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3878481686115265, "target_z": 0.025634763665010198, "ce": 6.205295085906982, "genuineness": 4.6203155517578125, "identity": 0.5938516855239868, "hypothesis": "La porte est encore ouverte, j'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/020f1687f57ccd3aa6868621bc69e7953a7c6ad5450e3a089933e5e67bf118e7.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "02ec2e0ba510d1c4df958bda383281c31c4e7ea29acd361c7c7f0e3155b383be", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "38c68ed817c171947635bbc5abbe1d20e09c2b5eb67dacfe98fcbd338e00d497", "generation_seconds_batch": 25.04595324397087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26636284589767456, "target_z": -0.14843751467907257, "ce": 6.141753673553467, "genuineness": 4.2249250411987305, "identity": 0.5324608087539673, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/02ec2e0ba510d1c4df958bda383281c31c4e7ea29acd361c7c7f0e3155b383be.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "02fff235708f102778baa74bfd942b599b08b7a24c0c736deec3dc19d5c5c1d5", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "7f340d13853784d0315804724763bb3f2f7d64ddec136c7f7fa8165f8b57aef4", "generation_seconds_batch": 26.54470519197639, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32020488381385803, "target_z": -0.07128904932219622, "ce": 6.149696350097656, "genuineness": 4.532451152801514, "identity": 0.6726394295692444, "hypothesis": "De beurs 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_Relief/02fff235708f102778baa74bfd942b599b08b7a24c0c736deec3dc19d5c5c1d5.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "031487e48968b50037d6c2fb567b7b4b3c33dc5d2e3c2cc081bdb601e764b7f6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3439ea6ebd5f7113385b49be26ad38385897ffc8a8f1e72b03cf670b5122e96c", "generation_seconds_batch": 26.69957619009074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18866677582263947, "target_z": -0.2597656293369987, "ce": 6.260893821716309, "genuineness": 4.545003414154053, "identity": 0.6231194138526917, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/031487e48968b50037d6c2fb567b7b4b3c33dc5d2e3c2cc081bdb601e764b7f6.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": "033b6d24f76ed2e757e3ac49431b8848b3c89004ce2834ca033e858035501183", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "737d7462b2382139080f02de81738691e57a2e7fa8e29da4732ff5013bf82ca8", "generation_seconds_batch": 23.187365590943955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1060256958007812, "target_z": 1.0546874559627823, "ce": 6.229123115539551, "genuineness": 4.118232727050781, "identity": 0.6147072911262512, "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_Relief/033b6d24f76ed2e757e3ac49431b8848b3c89004ce2834ca033e858035501183.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "03c1589e164d7f63974dedb2fac449c829b83e005ebf73d879bf9ed7e3b68652", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "93c6ac17beb6b9c680f049c72161314036219b8813924fc66459570c196be644", "generation_seconds_batch": 28.52753813401796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8688482046127319, "target_z": 0.7148437173057021, "ce": 6.260893821716309, "genuineness": 4.256305694580078, "identity": 0.5161730051040649, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/03c1589e164d7f63974dedb2fac449c829b83e005ebf73d879bf9ed7e3b68652.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": "03cb7b91e55688ada8f906369d90f02ef2c2732c33ceec29f415bae35fcc00ae", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "5a6d8e9b6dae24527e960ae6f1cddaf6d0b282bba3f4382aaac2ff642f736c22", "generation_seconds_batch": 16.62069625291042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42516273260116577, "target_z": 0.0791015613323465, "ce": 6.284721851348877, "genuineness": 4.6956281661987305, "identity": 0.22722400724887848, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam neem ze mee als je weg.", "wer": 0.045454545454545456, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/03cb7b91e55688ada8f906369d90f02ef2c2732c33ceec29f415bae35fcc00ae.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "047611b547fdda73e1e73da70ab2118a3d77beb6edea9a2a47fee3b8d43aaab4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9334a76dcdef35ab46730b776bfdf23172063b42bdf4b44bf30e3dcd7e04e773", "generation_seconds_batch": 26.865102300071158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.37864351272583, "target_z": 1.4453124586317045, "ce": 6.165581703186035, "genuineness": 4.413206577301025, "identity": 0.4227439761161804, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/047611b547fdda73e1e73da70ab2118a3d77beb6edea9a2a47fee3b8d43aaab4.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "050e3265591bdacfa33296126a11ef10077b32d8f000765cbac73082a7594edb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "31d56fd4b08b1998a550b34edd016f815e6e257cdebbf00a5156ef9cab15fbab", "generation_seconds_batch": 18.516532197012566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1278351545333862, "target_z": 1.0859375040033834, "ce": 6.205295085906982, "genuineness": 4.337893962860107, "identity": 0.27304887771606445, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/050e3265591bdacfa33296126a11ef10077b32d8f000765cbac73082a7594edb.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": "058fc086b420eec79557d2f4f4169db8c66022308d11c36002271eb2add28426", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "763924e6e3b9ba742c68f4e811fb5339a17f6465f2da6bff9f39c1b81154c04c", "generation_seconds_batch": 20.308469980955124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19752685725688934, "target_z": -0.24707031333403823, "ce": 6.292664527893066, "genuineness": 4.494794845581055, "identity": 0.7246391773223877, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het na de lunches 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_Relief/058fc086b420eec79557d2f4f4169db8c66022308d11c36002271eb2add28426.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "f16f22e3da894dfc5732a57a412622d15419d6b443daa152787236b6a58813fc", "generation_seconds_batch": 17.818637708900496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0460498332977295, "target_z": 0.9687500373649119, "ce": 6.332377910614014, "genuineness": 4.7332844734191895, "identity": 0.6118207573890686, "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_Relief/059867605942d1f4c46c2c44d936e08b7fbe89dd4feef4c05500a7ed426c27a3.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "05e0843e17fe2c26c4ce01f2c0fe9049fdaa5aae9deccf52261c1111ed220046", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "99a0d223d6c975feaf8ff717098a861c7cc756dea538024fe5a523d1b276683e", "generation_seconds_batch": 23.666474730009213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0951210260391235, "target_z": 1.0390625173479948, "ce": 6.006728172302246, "genuineness": 4.024092197418213, "identity": 0.6724255084991455, "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_Relief/05e0843e17fe2c26c4ce01f2c0fe9049fdaa5aae9deccf52261c1111ed220046.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "061fadf4fa9ead4931aa64bbc9693d933fa12d381ca7ee5651a6cedb7e25f34b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "0d851457fbd9f3a06872eaa8a229d7fd413c766b7004c22aade3e0ec8d8255bc", "generation_seconds_batch": 23.572377271018922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3515559136867523, "target_z": -0.026367201345034345, "ce": 5.903473377227783, "genuineness": 3.8671910762786865, "identity": 0.5976471900939941, "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_Relief/061fadf4fa9ead4931aa64bbc9693d933fa12d381ca7ee5651a6cedb7e25f34b.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "067411698622f4a107489b6aee2b1452c3bdcee431c22f902cac1f7b953df7a7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f65fe46318d655f42c9d74637a60ae5a0d10a0c07fc72db83709c50a16ff08be", "generation_seconds_batch": 21.886650168919004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5192158818244934, "target_z": 0.2138671906693452, "ce": 6.372091293334961, "genuineness": 4.231201171875, "identity": 0.3973020315170288, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/067411698622f4a107489b6aee2b1452c3bdcee431c22f902cac1f7b953df7a7.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": "06d7d854d1faea9e76fca105c3c2d6bc6df519ac3bb664ca8239a8b1248f9bdd", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7ff8746f37ab5ed84888b79bbffa548ecdef7e57534c2d08667687cbe6f5d7b1", "generation_seconds_batch": 22.887618473963812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.718908429145813, "target_z": 0.5, "ce": 6.0146708488464355, "genuineness": 4.6203155517578125, "identity": 0.8014342784881592, "hypothesis": "J'ai créé numero sur l'enveloppe, lile et verify the two dernier chiffres. Appelle moi quand you're a moment.", "wer": 0.5909090909090909, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/06d7d854d1faea9e76fca105c3c2d6bc6df519ac3bb664ca8239a8b1248f9bdd.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "077e30c7a9c0d290f602ef53ff28d88346d580fb0c8e393d132583ce93b5dd4f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "16c172b06ad0adc26f562a35a663d951d3243f9cf46af216731df5392a24e31a", "generation_seconds_batch": 25.305109695065767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1169304847717285, "target_z": 1.0703125653885959, "ce": 5.871703147888184, "genuineness": 3.9173994064331055, "identity": 0.662316083908081, "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_Relief/077e30c7a9c0d290f602ef53ff28d88346d580fb0c8e393d132583ce93b5dd4f.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "082aa1e0a27152342dd8325d0dddfd115235b3ddd1b576757b103ed8a4c6d57b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f99d8ae8af88767f070d678f7f816ba6a983b633929de3adaff8a69042b5d4e1", "generation_seconds_batch": 18.60131783701945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48990947008132935, "target_z": 0.17187500800676686, "ce": 6.252951145172119, "genuineness": 4.406930446624756, "identity": 0.6019189953804016, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/082aa1e0a27152342dd8325d0dddfd115235b3ddd1b576757b103ed8a4c6d57b.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "093ee0416fe40b622a9c37c936ba6d847f5d0fbb112f60322f4f1e705489f959", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6f761d4c82eeafc0d0757e3fb5f9e35014160426608a010536a64aee57333255", "generation_seconds_batch": 26.132597391027957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42516273260116577, "target_z": 0.0791015613323465, "ce": 6.2767791748046875, "genuineness": 4.406930446624756, "identity": 0.33416426181793213, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/093ee0416fe40b622a9c37c936ba6d847f5d0fbb112f60322f4f1e705489f959.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "096eea758419961dbfc30bf15053c59e407028a388917d8832eb7cde3ff2ffb4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "08367c41541fbd293c51755dc78e811481ce83ea472153aac84996a6bdf572a5", "generation_seconds_batch": 24.144749078084715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0133357048034668, "target_z": 0.9218750507095234, "ce": 5.816103935241699, "genuineness": 3.7291181087493896, "identity": 0.5727769136428833, "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_Relief/096eea758419961dbfc30bf15053c59e407028a388917d8832eb7cde3ff2ffb4.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "098c06bc4e9d33220e4efefa3436471a1f726ca6d51de2b8a2b0310fd100c477", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "360ef8cd4171c2ac288bd352e7b3db853a97a1c43ce691a6f571a37aac674cdc", "generation_seconds_batch": 18.385925302980468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6098613142967224, "target_z": 0.3437500160135337, "ce": 6.308549880981445, "genuineness": 4.758388519287109, "identity": 0.8474048376083374, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/098c06bc4e9d33220e4efefa3436471a1f726ca6d51de2b8a2b0310fd100c477.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "09ae6cbb3b99fb40e1df65b9f2a5386cf74169905e5da96689fc4d46ef78732d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "7d47b2d915a9c6538a0a9eff7dc28104eb47ce32419d08be79797546d56318e2", "generation_seconds_batch": 24.253472791053355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5335283279418945, "target_z": 0.23437501868245597, "ce": 5.919358730316162, "genuineness": 4.381826400756836, "identity": 0.4137250781059265, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/09ae6cbb3b99fb40e1df65b9f2a5386cf74169905e5da96689fc4d46ef78732d.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "0b2cf80e1a4af80256d951fd57a5cf970669b562cf353b234ddeafca7c3d3c2f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "19873d6b8cf67684d4ae9ec9bcd306638b59f01a083f855377deceba8d0c5d4e", "generation_seconds_batch": 25.6094871989917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5975934863090515, "target_z": 0.3261718533150064, "ce": 6.23706579208374, "genuineness": 4.218649387359619, "identity": 0.46484166383743286, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/0b2cf80e1a4af80256d951fd57a5cf970669b562cf353b234ddeafca7c3d3c2f.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": "0b4da254a39ee85de499856b8c994946d68b8eb437ce0a99f9f20510ad0f8a94", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "37bbe84cf153328423a56cd89f6ff7647438d9753dd661b6316bc890733115ce", "generation_seconds_batch": 17.447530281031504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3406512141227722, "target_z": -0.04199218266257836, "ce": 6.070269584655762, "genuineness": 4.482243061065674, "identity": 0.5173584222793579, "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_Relief/0b4da254a39ee85de499856b8c994946d68b8eb437ce0a99f9f20510ad0f8a94.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "0b777f92724b229e3df2244e127d7eb17ccbc8e940d2cb7947506e8d79afd08b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b70a69be6b4add9d5c2b53420d2a87483dac1225f80dd0e24f596b62590c4c9b", "generation_seconds_batch": 22.829820433049463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.498088002204895, "target_z": 0.183593754670614, "ce": 6.1020402908325195, "genuineness": 4.482243061065674, "identity": 0.559529185295105, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/0b777f92724b229e3df2244e127d7eb17ccbc8e940d2cb7947506e8d79afd08b.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "0ba68ef627c14524875aab1d57473c8eba8ef8e1a07a9f95be593f704b197f07", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "67b8d4c6e9e6a728fc4969713bc616f26e26fefbf09027158ca614202a9d0cfc", "generation_seconds_batch": 22.61509523296263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6507539749145508, "target_z": 0.40234374933276945, "ce": 6.260893821716309, "genuineness": 4.645420074462891, "identity": 0.624117374420166, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/0ba68ef627c14524875aab1d57473c8eba8ef8e1a07a9f95be593f704b197f07.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "0bab876f0735dd369c65da3f74fc4b8c92ad900e26014e091a357ba36c3b87ab", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3db7044c71364fade21cfd06913c9b5fe8a154c1e0bb09ddca24cf723fe5858c", "generation_seconds_batch": 27.128995870938525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.513081967830658, "target_z": 0.20507810932008158, "ce": 6.252951145172119, "genuineness": 4.068024158477783, "identity": 0.6038103699684143, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/0bab876f0735dd369c65da3f74fc4b8c92ad900e26014e091a357ba36c3b87ab.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "0bceb1d4bf84797a1c398d4e053675c03d95ed892be55cf0897d6d1c3ccbf021", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "11df1984e45827a5797210285719730ff8e600f144a3e4c9172fe4697e49298b", "generation_seconds_batch": 25.255235970951617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5812364220619202, "target_z": 0.30273435998731213, "ce": 6.419747352600098, "genuineness": 4.042920112609863, "identity": 0.4795267879962921, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/0bceb1d4bf84797a1c398d4e053675c03d95ed892be55cf0897d6d1c3ccbf021.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": "0bfd8c8e95d6a04d29a0f1dbf640b024f15af9299194c80616040334be7f4bf1", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "99f788d3d44a7964e140467cf71e5dd30729ebb8e09bb1ee127fffadc3f1c2cc", "generation_seconds_batch": 17.190826967009343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8715744018554688, "target_z": 0.7187499946621554, "ce": 5.855817794799805, "genuineness": 4.507347106933594, "identity": 0.775344967842102, "hypothesis": "Ya route tourna gauche après le pont continue just a la petite barrière en bois tattendre de l'autre côté.", "wer": 0.35, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/0bfd8c8e95d6a04d29a0f1dbf640b024f15af9299194c80616040334be7f4bf1.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": "0c73ba1b769087bec1cdf86cdf39cb9ef182c3dde6549491f0564c0d88022862", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "599acbd366fc50a8ac1216fdf1e9fd405d5d36ff98366ee5940728cfa9a401e4", "generation_seconds_batch": 23.12738968397025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2806752920150757, "target_z": -0.12792968666596177, "ce": 6.308549880981445, "genuineness": 4.519899368286133, "identity": 0.6385353803634644, "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_Relief/0c73ba1b769087bec1cdf86cdf39cb9ef182c3dde6549491f0564c0d88022862.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "0c7680dfc57e88c5a0ece63d6b981fee7c3e64f28c481048d630bc09149f9ffd", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "11da73b6dde04e2ec3982e2f250d7bca18c5d563e120d3abbad03939ea67ea6f", "generation_seconds_batch": 21.373594750999473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48104938864707947, "target_z": 0.15917969200380636, "ce": 6.372091293334961, "genuineness": 4.595211505889893, "identity": 0.6413065195083618, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/0c7680dfc57e88c5a0ece63d6b981fee7c3e64f28c481048d630bc09149f9ffd.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "08230115d3be98e74eaca088009da9b1d9c12288e7a25db18eb58d01e528c955", "generation_seconds_batch": 18.64568368392065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.03736388683319092, "target_z": -0.4765625066723057, "ce": 6.141753673553467, "genuineness": 4.344170093536377, "identity": 0.5758340358734131, "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_Relief/0cb70e86df8754d3bba44fe7f798aac7d0ffe2ca68fc75b92ff1a1ed29986ba7.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "0d626965ec67de9355180beabd085d04d1962d677165c7b9a47b06e1ae04322f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1c28d17b2aabd1c2d898fc489c615b69daf9a5ccd8e856810ecefd0d1b830c5c", "generation_seconds_batch": 28.52753813401796, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0296926498413086, "target_z": 0.9453123732261915, "ce": 6.181467056274414, "genuineness": 4.457139015197754, "identity": 0.5524646043777466, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/0d626965ec67de9355180beabd085d04d1962d677165c7b9a47b06e1ae04322f.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "0d8cbc31117b90ae6cb1c36a75a7acdc9e4ba8631ac964753c0adf1bdffc2854", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7d4d9f124b9b7a44f78a846cf63134fbd5c6cf9335db8fd45b1fe77e6d823b98", "generation_seconds_batch": 28.590444909990765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9751691818237305, "target_z": 0.867187509341228, "ce": 6.252951145172119, "genuineness": 4.419482707977295, "identity": 0.33714333176612854, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/0d8cbc31117b90ae6cb1c36a75a7acdc9e4ba8631ac964753c0adf1bdffc2854.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "0da283fa65c5fa19db410b262ec672bf29f23ee63e03077bc7422e9ec132b470", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ba98872eea504d275a2391943a12dc7e2650ee7a99d7cf2829aace72fb73365d", "generation_seconds_batch": 22.337986020022072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.986073911190033, "target_z": 0.8828125333615285, "ce": 6.062326908111572, "genuineness": 4.193545341491699, "identity": 0.43054988980293274, "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_Relief/0da283fa65c5fa19db410b262ec672bf29f23ee63e03077bc7422e9ec132b470.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "0e4084ffa2b3ba750047e52bdc2e58e4147984650fd1a20d4c900247a95a9843", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d8fa6a742700a3eb64f1bd84ddfb5a2f3d967e69ba8fb423d5e09fbde802ece2", "generation_seconds_batch": 18.08021842793096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7461702227592468, "target_z": 0.5390625173479948, "ce": 6.308549880981445, "genuineness": 4.231201171875, "identity": 0.5713932514190674, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/0e4084ffa2b3ba750047e52bdc2e58e4147984650fd1a20d4c900247a95a9843.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "0e460ff8741609034b1631725a286e2e174170889eba5b827c1f37f43c4c26ca", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "025aba40dfc6367286d0bf15561f3a79aa0be4261353e22b902c09666e69b10d", "generation_seconds_batch": 16.24264996103011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6780157685279846, "target_z": 0.44140626668076427, "ce": 6.229123115539551, "genuineness": 3.9048471450805664, "identity": 0.22827090322971344, "hypothesis": "The 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_Relief/0e460ff8741609034b1631725a286e2e174170889eba5b827c1f37f43c4c26ca.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "0e5641e9870c9230f9fb01a3692d11a69581f0d22ce4af55632bbde9f3818dd1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "3d6b829e3d28c2cce10f5ac073d36213e56cd325dd02ff5114efd8b3b1723d67", "generation_seconds_batch": 29.7563175780233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8529984951019287, "target_z": 2.124999935945865, "ce": 6.308549880981445, "genuineness": 4.149612903594971, "identity": 0.313310831785202, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/0e5641e9870c9230f9fb01a3692d11a69581f0d22ce4af55632bbde9f3818dd1.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "0ed13d63e4d5eb7001820934206482c9373e212982ca131881fd2dcf96097ddc", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6b2e8c25216efa4380f33377846e857916e0f58f25cc19826bd364372d0c2c6d", "generation_seconds_batch": 18.530412995023653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22410710155963898, "target_z": -0.2089843653251567, "ce": 6.2767791748046875, "genuineness": 4.444586753845215, "identity": 0.4819439649581909, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/0ed13d63e4d5eb7001820934206482c9373e212982ca131881fd2dcf96097ddc.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "0f5d1de814a8aab131d4b0a63c648af68041205a613ba3cee476c4b39954b826", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c59979aa673a0e0f6d5aaffae5b8faac44043c6d5cd6b2cebd4896eb9bfcff2d", "generation_seconds_batch": 24.497134496923536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.838860273361206, "target_z": 0.6718750080067668, "ce": 5.903473377227783, "genuineness": 4.055472373962402, "identity": 0.5572502613067627, "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_Relief/0f5d1de814a8aab131d4b0a63c648af68041205a613ba3cee476c4b39954b826.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "0f688b80429f381f59e8dda63fd22da3ba139e3273873c55e3ca5ab71f67c0eb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6523e0e56ce93a50c7d01c3afbfd448386dbb56978fc08839a351439e082fd7e", "generation_seconds_batch": 28.299006946966983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5362545251846313, "target_z": 0.23828129603890938, "ce": 6.09409761428833, "genuineness": 4.18099308013916, "identity": 0.39096030592918396, "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_Relief/0f688b80429f381f59e8dda63fd22da3ba139e3273873c55e3ca5ab71f67c0eb.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "0fa90a2afda4afa6dde63a298cc0ea7ebd1b1a6393bb6b53dde4cb191ceb373d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a84d9b6ad9299e2b397d3ba63a65ef044383cae5b749f02f3822ea28cdb29c45", "generation_seconds_batch": 27.348741577006876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6998251676559448, "target_z": 0.4726562293158523, "ce": 6.395919322967529, "genuineness": 4.394378662109375, "identity": 0.5940970182418823, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/0fa90a2afda4afa6dde63a298cc0ea7ebd1b1a6393bb6b53dde4cb191ceb373d.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": "1027c0838a7681847dd2ac3ff7ad8965ed9024725abf0555384b260f0a3bf84e", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "41094fd7011d8348b866418fff40a4583ec54805f32e93ab2989bf8319827c40", "generation_seconds_batch": 17.274418262997642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.718908429145813, "target_z": 0.5, "ce": 6.284721851348877, "genuineness": 3.998987913131714, "identity": 0.08995644748210907, "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_Relief/1027c0838a7681847dd2ac3ff7ad8965ed9024725abf0555384b260f0a3bf84e.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "1092eee53b9c773099678129ad72b141c70fc377e79bc1c9417e6a8989f2006e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fe70ffc5102e4d3ca86f112b340e04c5499a7b29fc23f3ba6d6d35b3d981314a", "generation_seconds_batch": 16.422688933089375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8633958697319031, "target_z": 0.7070312479983083, "ce": 6.459460258483887, "genuineness": 4.218649387359619, "identity": 0.5720483064651489, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1092eee53b9c773099678129ad72b141c70fc377e79bc1c9417e6a8989f2006e.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "10eda69fefe74ac048a93907f44bc959badb47111ff107eabf157e3ef0dc3616", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "135f7cd159a7d3f46b13630fbf21c1620ef2eba362a4f08027374d0e1e436b0d", "generation_seconds_batch": 22.829820433049463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2859535217285156, "target_z": 1.3125000533784457, "ce": 6.1020402908325195, "genuineness": 4.118232727050781, "identity": 0.5436620712280273, "hypothesis": "Te he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/10eda69fefe74ac048a93907f44bc959badb47111ff107eabf157e3ef0dc3616.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "10f0ad6362e9e2cd162a7364b7674e3d3c5a0bf60e6ff0b58cf23f7cde9dcc30", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "11e34b23c8ba6dfdbbb78cd71e0375fe5a622eb629b82b725abbdf8b5fefb5dd", "generation_seconds_batch": 28.607052302919328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07689347863197327, "target_z": -0.41992186932854014, "ce": 6.070269584655762, "genuineness": 4.344170093536377, "identity": 0.7317265272140503, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/10f0ad6362e9e2cd162a7364b7674e3d3c5a0bf60e6ff0b58cf23f7cde9dcc30.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "11898795d10149a018847b5ec51481c29a1ec299abd6d26ceeba11af0256b968", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "3d5ce5b6d11c784f65822105f4ee67c310876dcd7f78dc9117af03dc757d0390", "generation_seconds_batch": 27.934305061004125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37575075030326843, "target_z": 0.008300775328328684, "ce": 6.300607204437256, "genuineness": 4.469690799713135, "identity": 0.5550453662872314, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/11898795d10149a018847b5ec51481c29a1ec299abd6d26ceeba11af0256b968.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "11acea4d51b56d8f19c22591df3779444aa3844da2ebb3d71eb8a09260637a46", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6c4aba3fda5cef28cd0d329cefcd29c9a39f464b6617e146d91b937d58ab905a", "generation_seconds_batch": 16.840185210923664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8988361954689026, "target_z": 0.7578125120101503, "ce": 6.459460258483887, "genuineness": 4.149612903594971, "identity": 0.3256455063819885, "hypothesis": "Ich hab die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.125, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/11acea4d51b56d8f19c22591df3779444aa3844da2ebb3d71eb8a09260637a46.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "12120eae0895a4509c4999e63f171e084ce29822f54ad17b198cc8bed197a015", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "feaacf60bafb43ea35c490c9f1f10b2a85b69b5527a88dc7d3776330879d351b", "generation_seconds_batch": 18.492925032041967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4113576412200928, "target_z": 1.4921874452870931, "ce": 6.181467056274414, "genuineness": 4.250029563903809, "identity": 0.4890426695346832, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre.", "wer": 0.3684210526315789, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/12120eae0895a4509c4999e63f171e084ce29822f54ad17b198cc8bed197a015.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "1212b7b5c23adc297dd0507f19b3ef67acdcdcd342d02ee3173c074869683280", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b71daa1c2e81e83d248e3f8e6c670c7fbe4782ed0fd9ddc4af69bc8a18ee2b29", "generation_seconds_batch": 25.583574846968986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1600419133901596, "target_z": -0.30078124266046374, "ce": 5.935244083404541, "genuineness": 4.218649387359619, "identity": 0.6294354200363159, "hypothesis": "De deur 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_Relief/1212b7b5c23adc297dd0507f19b3ef67acdcdcd342d02ee3173c074869683280.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "1267d229382384a14906e612b30d526b48078e46d80c511431fc499e2deb58a3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "740fd03b5a1e26e2c9d30a4d570635f309d0772ee79e2dd26b70e48068f8c03f", "generation_seconds_batch": 29.40030817000661, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9560859203338623, "target_z": 0.8398437386570803, "ce": 5.808161735534668, "genuineness": 3.9550557136535645, "identity": 0.499586284160614, "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_Relief/1267d229382384a14906e612b30d526b48078e46d80c511431fc499e2deb58a3.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "127f7c0c5b29f779fea62124218250bccf62c010e62c83b9d98c32cb092840b4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "85a1f7e58ecb1b26f655fc903369b59939251c19b17c38104287b3ae081dce2e", "generation_seconds_batch": 23.425523838959634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8225032091140747, "target_z": 0.6484375146790725, "ce": 6.507116317749023, "genuineness": 4.281409740447998, "identity": 0.5593754053115845, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschreben.", "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_Relief/127f7c0c5b29f779fea62124218250bccf62c010e62c83b9d98c32cb092840b4.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "f7124b3e439eeeae2902c755e7dc95b6923b6e613d505c7970a02a7055b53e47", "generation_seconds_batch": 20.788874376914464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.893383800983429, "target_z": 0.7499999572972434, "ce": 6.252951145172119, "genuineness": 4.469690799713135, "identity": 0.6470309495925903, "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_Relief/12a7b850c68b1e935d69d2b179f3c0df54c4775061935760902fd9f6cbfc7541.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "12b0d13964f5952794191c1d0c18edaa6e6b95b89958fbf552faf8cac2ad663f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "63502f9c8e1a4d346bb01d8b2b4106485fb0259487c2a9f7c125a58905cedc25", "generation_seconds_batch": 22.699557490996085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3840959072113037, "target_z": 1.4531250133446114, "ce": 6.213237762451172, "genuineness": 4.369274139404297, "identity": 0.34792494773864746, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/12b0d13964f5952794191c1d0c18edaa6e6b95b89958fbf552faf8cac2ad663f.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "12fcc92eafb46b990f201a76303f2082d13fd30c5320e948f8300b7a4c30dd4e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6a7b52c70f03df4ea306e0d244d72092da9412120b5289a87f45588bfb8b181f", "generation_seconds_batch": 25.024381004972383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3144117593765259, "target_z": -0.07958982465052492, "ce": 6.1894097328186035, "genuineness": 4.419482707977295, "identity": 0.5732623338699341, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/12fcc92eafb46b990f201a76303f2082d13fd30c5320e948f8300b7a4c30dd4e.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": "13321aee2516eff7cabaaf42def26ebae6ee539c3926a1a114a0259ca7abf28f", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c6c37ea49aa2053b07b1d469a002f9f196a06174ce1d228022a6c8febefb2570", "generation_seconds_batch": 21.21970437199343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5498853921890259, "target_z": 0.25781251201015026, "ce": 6.1020402908325195, "genuineness": 4.413206577301025, "identity": 0.7077617645263672, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí junto a la estantería alta. La colocaremos después de comenzar.", "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_Relief/13321aee2516eff7cabaaf42def26ebae6ee539c3926a1a114a0259ca7abf28f.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "134065f34e90392a3a6f0d103a2bac75547ba819f06d6fff01e943db031b7ff9", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "894df6f8f0b61eeec3ad1eea3b290a51a7cd1251a4d53ee08dc4403325334ce1", "generation_seconds_batch": 17.364498949958943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.415961891412735, "target_z": 0.06591798201120759, "ce": 6.2767791748046875, "genuineness": 4.469690799713135, "identity": 0.46847695112228394, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/134065f34e90392a3a6f0d103a2bac75547ba819f06d6fff01e943db031b7ff9.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "13bfad1b0d9ee7df5e61f281c3d91713f5d814493b5913e938bc681d78369225", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "5b028b926091fdf49204aed9095df28bb587fa9736129f4f5b23760397e2e05f", "generation_seconds_batch": 23.050818285904825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3404769897460938, "target_z": 1.3906249172634093, "ce": 6.149696350097656, "genuineness": 4.193545341491699, "identity": 0.6884867548942566, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce quelqu'un.", "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_Relief/13bfad1b0d9ee7df5e61f281c3d91713f5d814493b5913e938bc681d78369225.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "13ca4c86934a7614fc1d51bf08916cddd54afced10568a457700014eef4eabf9", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e36ad0863ed08a0280460b907e93e9302b842e9a10774824f1c244a79675567b", "generation_seconds_batch": 23.355500111938454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8748080730438232, "target_z": 2.1562501547974926, "ce": 6.149696350097656, "genuineness": 4.413206577301025, "identity": 0.7779659032821655, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre.", "wer": 0.3684210526315789, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/13ca4c86934a7614fc1d51bf08916cddd54afced10568a457700014eef4eabf9.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "1492c8111f0d14f0d5ae5ed08ff477bd7572d0888745a6b6a7231b365372853a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "804aad8665056645ac1438c4f40761e29a2509b4c38c60d6c43361ad88a78812", "generation_seconds_batch": 27.260622228030115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6098613142967224, "target_z": 0.3437500160135337, "ce": 6.109982967376709, "genuineness": 4.369274139404297, "identity": 0.6324903964996338, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1492c8111f0d14f0d5ae5ed08ff477bd7572d0888745a6b6a7231b365372853a.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "14b7740bb8481793b7dc2c6992da9f59f928ad7c74ee5669eb765829c907636e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "2d58005063f4df522ef2457118c02372186e4d006dc49610f2217f486c3a7320", "generation_seconds_batch": 24.449274851940572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7625272870063782, "target_z": 0.5625000106756891, "ce": 5.990842819213867, "genuineness": 4.319066047668457, "identity": 0.5526920557022095, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/14b7740bb8481793b7dc2c6992da9f59f928ad7c74ee5669eb765829c907636e.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "14fc32954e0280870faba771d176586b63cd0ca7518faa96562da6fb3aa265c7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e48c80496d968bc30d6893528daea7429a44badb4982e67a2505a8d5eb32101e", "generation_seconds_batch": 25.323077872977592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6684741377830505, "target_z": 0.4277343813386904, "ce": 6.117925643920898, "genuineness": 4.068024158477783, "identity": 0.5510551333427429, "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_Relief/14fc32954e0280870faba771d176586b63cd0ca7518faa96562da6fb3aa265c7.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "1508059d5d0169dddfdedc9b9112efd67291f4b3fb0c4bc96cc8077b3d892943", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57c6eee9455f4ee60cf10aeabc88104322d2f83568b4ba6ececacc4fa630b4ee", "generation_seconds_batch": 24.464805445051752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2150728702545166, "target_z": 1.2109375253547616, "ce": 6.23706579208374, "genuineness": 4.425758361816406, "identity": 0.7605071067810059, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1508059d5d0169dddfdedc9b9112efd67291f4b3fb0c4bc96cc8077b3d892943.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": "150ff25dc07393f0e1d948ee5556988a6639e50866906384697184382bb7f755", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a68e0536db9b548882c9b22c402a163e58c74f1f84b79e3471d3bb96fb0ae630", "generation_seconds_batch": 21.785958433058113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1709466278553009, "target_z": -0.28515623999154144, "ce": 6.117925643920898, "genuineness": 4.400654315948486, "identity": 0.5914985537528992, "hypothesis": "De weg gaat linksaf naar de brug. Loopt verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/150ff25dc07393f0e1d948ee5556988a6639e50866906384697184382bb7f755.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "1549327f0f683aafff7f401c05c1696ad572d5def209c7f370d23aeb0cdfee37", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "ab41fcce5b9d9a67364db30d44bb9a45cadcdc2df7e4ec5d25f254845a3a9739", "generation_seconds_batch": 16.22829673695378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9838550090789795, "target_z": 2.3124998825674195, "ce": 6.252951145172119, "genuineness": 4.218649387359619, "identity": 0.3382967710494995, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1549327f0f683aafff7f401c05c1696ad572d5def209c7f370d23aeb0cdfee37.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "4823242dd0e6e247857a8a9ae779ff79ad1e2dfbac6ceecda309b95c352b1e90", "generation_seconds_batch": 17.189651445951313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5308021306991577, "target_z": 0.2304687413260026, "ce": 6.260893821716309, "genuineness": 4.262581825256348, "identity": 0.6115658283233643, "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_Relief/15585f3962d31fd159bb39a755593ab24aa0df87e4725d7772f40811258760f5.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "15c98e61267835bd1ffcfa5ce4322ebfae4e32c8c0b7b2a2b77ed0765ff48332", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8d9eb5cf9b27e83368c7c7fbbbe77ca3c61e8167123f688b5b9a582dd86e3ba2", "generation_seconds_batch": 24.832501029013656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5694761276245117, "target_z": 1.7187501654731816, "ce": 6.078212261199951, "genuineness": 4.18099308013916, "identity": 0.6614900827407837, "hypothesis": "I've done the petite boîte. It is pretty lay fenêtre. We'll regard what it is.", "wer": 0.8421052631578947, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/15c98e61267835bd1ffcfa5ce4322ebfae4e32c8c0b7b2a2b77ed0765ff48332.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": "15fa0c83e2baeaa1082062d6d5c3f691df65d7127b3210a38d0e05d7528ccb3e", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d5adbdaf2db0fe2d2350ac7b5c9cc6ed45208425e18ae2c9e707a5f46431d0b6", "generation_seconds_batch": 19.564371157088317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7298130989074707, "target_z": 0.5156249386147875, "ce": 6.086154937744141, "genuineness": 4.306513786315918, "identity": 0.5845493078231812, "hypothesis": "J'ai le numéro sur l'enveloppe, le bien and two dernier chiffres. Appelle moi quand you're a moment.", "wer": 0.45454545454545453, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/15fa0c83e2baeaa1082062d6d5c3f691df65d7127b3210a38d0e05d7528ccb3e.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "168e66fa6527385839433a64a551fad8af21c50b1c80380302dc0db4ff3dc207", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1b5f7a5742b35dfd9d835f5c33060dc9c1bff33e4447387a0f79968be6cef8f2", "generation_seconds_batch": 24.627454808098264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0133357048034668, "target_z": 0.9218750507095234, "ce": 6.41180419921875, "genuineness": 4.218649387359619, "identity": 0.5637220144271851, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/168e66fa6527385839433a64a551fad8af21c50b1c80380302dc0db4ff3dc207.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "168f018436aa76be3d16a08cb2b658f8639c2709d6ef2a4d2ed63b155b9347b4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3723aa246db9c4adbb5e14fe645be20283adcbc99cd91e59c95418b215f04287", "generation_seconds_batch": 25.86161808401812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4953618049621582, "target_z": 0.1796874773141606, "ce": 6.24500846862793, "genuineness": 4.425758361816406, "identity": 0.6378371715545654, "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_Relief/168f018436aa76be3d16a08cb2b658f8639c2709d6ef2a4d2ed63b155b9347b4.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "169ab0b4428313225948ef0603c706728ee5214da04dd9df54eff2e9868b498b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd5f696309c4e29ab9a426936051e4724fa376620edeb971057e6d8e9ae2ac40", "generation_seconds_batch": 27.049043647013605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1278351545333862, "target_z": 1.0859375040033834, "ce": 6.348263263702393, "genuineness": 4.507347106933594, "identity": 0.7601296901702881, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/169ab0b4428313225948ef0603c706728ee5214da04dd9df54eff2e9868b498b.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "17011e69e997839eabbc626a3c890be807565be571e36878acbe41648e6b7ac5", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5feed4dd69d848fc12ed38f542a64e15e99222b3dee578532e253bc3bb9de32e", "generation_seconds_batch": 23.282256457023323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.517852783203125, "target_z": 0.2119140519911185, "ce": 6.348263263702393, "genuineness": 4.519899368286133, "identity": 0.6315453052520752, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/17011e69e997839eabbc626a3c890be807565be571e36878acbe41648e6b7ac5.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": "1718ca2fc6c8485282751a5163fc8beccc781b821a5632702e62d3abdab0cac0", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7315090fbdec1cc4899928a4ca0ca7d1ba57cc2afa47598bde6208ea99f1f605", "generation_seconds_batch": 16.7769504430471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3386065661907196, "target_z": -0.04492189067991841, "ce": 6.395919322967529, "genuineness": 4.632867813110352, "identity": 0.5149393081665039, "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_Relief/1718ca2fc6c8485282751a5163fc8beccc781b821a5632702e62d3abdab0cac0.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "180c0681ef1a63a13b4ea32b0687a857dd86315a2985a89ee91655f5a3d25663", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "735ea4213ee57a997385256952f01771eaa90c51fbbe8c0cd15ba34e0bd9c19d", "generation_seconds_batch": 24.136092718923464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9451811909675598, "target_z": 0.8242187146367798, "ce": 6.2767791748046875, "genuineness": 4.413206577301025, "identity": 0.19810260832309723, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/180c0681ef1a63a13b4ea32b0687a857dd86315a2985a89ee91655f5a3d25663.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": "18330ed9b5bb63fe9ecf5318e1ff941af6d6107e6b5c50cc13c158e3b836a1dc", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4d7812f61a102a1fcd95d682e0715bda2a0d5c8c5f0f13592d92cfba45cb32e5", "generation_seconds_batch": 19.490673589985818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43265971541404724, "target_z": 0.0898437386570803, "ce": 6.165581703186035, "genuineness": 4.457139015197754, "identity": 0.7005159258842468, "hypothesis": "Calca a déplacé la petite chaise bleue. Elle était ici près de la grande bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/18330ed9b5bb63fe9ecf5318e1ff941af6d6107e6b5c50cc13c158e3b836a1dc.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "1853a1c9d4967a36ca96ba22e03988c3c333cfcdd708e76cae408a959408f86c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "40632cba1ea8929299c594c33be8713815f3cc74cba7246d1a76a72fecc121ab", "generation_seconds_batch": 25.789295181981288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5042219161987305, "target_z": 0.19238283601987763, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.5823166370391846, "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_Relief/1853a1c9d4967a36ca96ba22e03988c3c333cfcdd708e76cae408a959408f86c.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "18c35a1d4e44b6792b898a72d051f3d7758754337034faf6c190003b6c010e6e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a2ee458f98fd4d30e429527ab6925da400e1f2ef04c1cd20fe3daf9859702b23", "generation_seconds_batch": 27.027711601927876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1278351545333862, "target_z": 1.0859375040033834, "ce": 6.24500846862793, "genuineness": 4.507347106933594, "identity": 0.37589892745018005, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/18c35a1d4e44b6792b898a72d051f3d7758754337034faf6c190003b6c010e6e.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "1912b95d4e7a97664aca9418e46860ce44f2f5b80449f260b891b6874e0d5e85", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "712914bdbdd4cf484e1fa811895de3ad714469c7184c8ff967af05e3ad4e524c", "generation_seconds_batch": 16.622751369024627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3622864484786987, "target_z": 1.4218749653040104, "ce": 6.38003396987915, "genuineness": 4.325342178344727, "identity": 0.407284140586853, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1912b95d4e7a97664aca9418e46860ce44f2f5b80449f260b891b6874e0d5e85.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "195ded6e41dd137267bbab298dc8f2b5f0233a0775cf0a8e19332bd8f38fdb32", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "158eedb349aea06fea6174c3500bba16ba164c73988b962d8c23f182b94f039b", "generation_seconds_batch": 19.735312632052228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3075962960720062, "target_z": -0.08935547533890188, "ce": 6.268836498260498, "genuineness": 4.406930446624756, "identity": 0.5333769917488098, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/195ded6e41dd137267bbab298dc8f2b5f0233a0775cf0a8e19332bd8f38fdb32.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "195e7a3785adbad4f4305da5e0191298a2e2d4dd659b37b9c5a7ed416adea13b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dfd4a1759056e2a4461636c00709de11b496b180b2bc4708a1f928a81f268ddb", "generation_seconds_batch": 23.856130195083097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0951210260391235, "target_z": 1.0390625173479948, "ce": 6.221180438995361, "genuineness": 4.3127899169921875, "identity": 0.623902440071106, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/195e7a3785adbad4f4305da5e0191298a2e2d4dd659b37b9c5a7ed416adea13b.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "19af1fe61db3cc2e37f7750a9d024f7be46718d981cce66a8a8f628b810c511e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "4f4d6037816c073d4fde786f53ac2d11706473ddb3bdfe683c269033ac392058", "generation_seconds_batch": 15.914702903013676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5321652293205261, "target_z": 0.23242188000422928, "ce": 6.046441555023193, "genuineness": 4.494794845581055, "identity": 0.45145657658576965, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/19af1fe61db3cc2e37f7750a9d024f7be46718d981cce66a8a8f628b810c511e.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "1ac1fda8802e12587060b0dfff3d54b6fb5323c08aab41c5ac221319d99995a4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "39c2284a11ba06494cc9f22de2f450e535e674d34395e21b6dcd8ac4c9b23740", "generation_seconds_batch": 22.39610866107978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8497649431228638, "target_z": 0.6874999466215543, "ce": 6.221180438995361, "genuineness": 4.494794845581055, "identity": 0.5140324234962463, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1ac1fda8802e12587060b0dfff3d54b6fb5323c08aab41c5ac221319d99995a4.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "1b2a7ed7f3fed9c5a1eb2902178b4eeb0a43436d8d9598dc0a63db5aafa92e26", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "402fd74feabbf0b608610b84c5d0de96b0247e554ce7629d8ba7e5b6263cfbb9", "generation_seconds_batch": 25.190532780019566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5526115894317627, "target_z": 0.2617187893666037, "ce": 6.221180438995361, "genuineness": 4.519899368286133, "identity": 0.6058435440063477, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1b2a7ed7f3fed9c5a1eb2902178b4eeb0a43436d8d9598dc0a63db5aafa92e26.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "1b838723019225387ac013fc4b02d67ee0d7470e88ad6e538454a693c5134165", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "88a76ddcd633cd915048e1e7d12c6204b0c4fe26fb8ad064be67f6fb5d7d1f65", "generation_seconds_batch": 26.263341599027626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2259775400161743, "target_z": 1.2265624639695492, "ce": 6.09409761428833, "genuineness": 4.036643981933594, "identity": 0.33887243270874023, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1b838723019225387ac013fc4b02d67ee0d7470e88ad6e538454a693c5134165.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": "1b96d47e494bfdd16c4908390fe5725e9ad60cb70ca4a6bfe940b3980058d1db", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d0b9151b8bbe56af2d0b8b654b462f54dcfeeb0ae330fdc0b6dd394bedb0345c", "generation_seconds_batch": 18.115210441988893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2813568413257599, "target_z": -0.12695311732684844, "ce": 6.348263263702393, "genuineness": 4.607763767242432, "identity": 0.5926780700683594, "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_Relief/1b96d47e494bfdd16c4908390fe5725e9ad60cb70ca4a6bfe940b3980058d1db.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": "1ba0c08d1b81f3637bba900a8ad51875d611d862e40b740ae34aa500a11e1192", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "523e44864b0b499bef1d3cd00b1c6fbfcdaba1a510063ce37764df3824806bf0", "generation_seconds_batch": 23.96158161899075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24319034814834595, "target_z": -0.1816406159923873, "ce": 6.308549880981445, "genuineness": 4.218649387359619, "identity": 0.4877714216709137, "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_Relief/1ba0c08d1b81f3637bba900a8ad51875d611d862e40b740ae34aa500a11e1192.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "1c386f250db97d4ea760ce74b65bbbce5295c3428b312f381a3de3156767621c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "44b2dd8932ac50f8de5de1f41b97d328b453580a77c08891e8e4684e8110b057", "generation_seconds_batch": 21.32864022802096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6343969106674194, "target_z": 0.37890625600507516, "ce": 6.252951145172119, "genuineness": 4.093128204345703, "identity": 0.3390362858772278, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1c386f250db97d4ea760ce74b65bbbce5295c3428b312f381a3de3156767621c.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": "1c39e9f28781dbae6dc14f8835e9a9c3cc97a7e3021fa19c205d253f9e082fe8", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4f23819586f4c3f1e668f92150e55285c14e2131bda45f03e305068c89d01cce", "generation_seconds_batch": 19.786414239089936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2391010820865631, "target_z": -0.18749998932431086, "ce": 6.284721851348877, "genuineness": 4.532451152801514, "identity": 0.6276898384094238, "hypothesis": "Ik schreef het nummer op de envelop. Lees het goed en controleer de laatste twee cijfers. Bel me wanneer je even thuis hebt.", "wer": 0.043478260869565216, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1c39e9f28781dbae6dc14f8835e9a9c3cc97a7e3021fa19c205d253f9e082fe8.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "1cb2bf285bd03bc3d7c3ebfe0916d91801a90201f943d932e9e5f8b9a8890ea6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9816074e049154a59ab22f6ac1b2d13bc02a05e94e05e741ee40b5b46a16423d", "generation_seconds_batch": 24.049309851950966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6562063694000244, "target_z": 0.4101563040456762, "ce": 6.300607204437256, "genuineness": 4.419482707977295, "identity": 0.7396594285964966, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1cb2bf285bd03bc3d7c3ebfe0916d91801a90201f943d932e9e5f8b9a8890ea6.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "1d30c26155ca5a8babf8a452c970aabbfc3f20a306947da67e27947ee87fdec3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "616d102ace229f7745976c3af3e3b9daee1db09a2209917db973407ce970f4ef", "generation_seconds_batch": 21.307309853029437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6589325070381165, "target_z": 0.4140624959966166, "ce": 6.09409761428833, "genuineness": 4.494794845581055, "identity": 0.38362035155296326, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1d30c26155ca5a8babf8a452c970aabbfc3f20a306947da67e27947ee87fdec3.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "e0b2f5dd19f0f39b83ffb344952796af871a1b36c00f893ccc39613e5d0b2a83", "generation_seconds_batch": 21.128353408072144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.789789080619812, "target_z": 0.6015625280236839, "ce": 6.3641486167907715, "genuineness": 4.507347106933594, "identity": 0.6720905303955078, "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_Relief/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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "c8103041eea85abba2ac39ff512ccd71a0b84a78e33d03e5bd4b016158d44b82", "generation_seconds_batch": 17.063584667048417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21252083778381348, "target_z": -0.22558593733319235, "ce": 6.284721851348877, "genuineness": 4.482243061065674, "identity": 0.5061149597167969, "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_Relief/1d829402ab2176d2024ae3e918286a39ec094d9a5299caa0e048ba37912e1579.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": "1d83536da13c06d203944a98285620124a3f6b3674553ac80e3853f17e94f595", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7068a7ba007b6775ba445ffa724b2806c2c0b8f15d1377818ca918adf425e160", "generation_seconds_batch": 19.786414239089936, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1709466278553009, "target_z": -0.28515623999154144, "ce": 6.173524379730225, "genuineness": 4.444586753845215, "identity": 0.6371517777442932, "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_Relief/1d83536da13c06d203944a98285620124a3f6b3674553ac80e3853f17e94f595.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "1d930eefaf81764c4acace4f0a3647c513a5318371d6cb2c18769da441312f89", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "4836e4c89c417e9c0bea6fcddc982b2b3638ad22b137295ea2a5da7b4b923167", "generation_seconds_batch": 18.742833688040264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2968581914901733, "target_z": 1.3281249919932332, "ce": 6.125868320465088, "genuineness": 4.344170093536377, "identity": 0.5200469493865967, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay?", "wer": 0.058823529411764705, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1d930eefaf81764c4acace4f0a3647c513a5318371d6cb2c18769da441312f89.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "1da2a150202104248eaee7cf78d01c2df7315bb7cc89ad5862f74468ce92f4ad", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "2d08efd7f3ff38f885dd8b1c2ad2c4c09c2f55cb8f1f31bceef909e6561d4bc2", "generation_seconds_batch": 23.709191934904084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2150728702545166, "target_z": 1.2109375253547616, "ce": 6.308549880981445, "genuineness": 4.331617832183838, "identity": 0.7793376445770264, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1da2a150202104248eaee7cf78d01c2df7315bb7cc89ad5862f74468ce92f4ad.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "1e2c10869096abc440e387fe3a09302a8d586e19e673b9e3641af1f91514e1f7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "3b61217a17f0d76e76e84b4aab07b61991d85bfed87f3fdcbd06f3c9d245e5cd", "generation_seconds_batch": 24.205844998010434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3573490381240845, "target_z": -0.01806642601670566, "ce": 6.356205940246582, "genuineness": 4.457139015197754, "identity": 0.5150840878486633, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1e2c10869096abc440e387fe3a09302a8d586e19e673b9e3641af1f91514e1f7.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "1e7dcbbd8f0ba105d25a5a8a9fcefdd335f430a75f5e8740bc6339cef09cefa0", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "c7551806ff35758c0bb77ec9d80f63fe7af157c1151aad61d5819fbef2fd2922", "generation_seconds_batch": 23.263297195080668, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8770267367362976, "target_z": 0.7265624639695492, "ce": 5.657250881195068, "genuineness": 4.005263805389404, "identity": 0.44923532009124756, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás libre.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1e7dcbbd8f0ba105d25a5a8a9fcefdd335f430a75f5e8740bc6339cef09cefa0.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "ba9e3382e6863167c284879b3dc5dca0c40b7339611569c0297e678ccb1cdab2", "generation_seconds_batch": 21.128353408072144, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2581843137741089, "target_z": -0.16015626134291971, "ce": 6.308549880981445, "genuineness": 4.331617832183838, "identity": 0.7280136942863464, "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_Relief/1eaf0e0e2c966186cf6ada2de41819a315f8b1b1eeeeef5a84a28dd582998db8.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "1ecfb6f81483facd99ca2585c19b3eac7fc9277c91917a81b309d21614d411ac", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "383c09ce207f103550a775d58c7e8f0b57a8ed9da2fc2fcbcd617a1870a96d72", "generation_seconds_batch": 18.16742026398424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6112244129180908, "target_z": 0.3457031546917604, "ce": 6.229123115539551, "genuineness": 4.074300289154053, "identity": 0.32000309228897095, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1ecfb6f81483facd99ca2585c19b3eac7fc9277c91917a81b309d21614d411ac.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "1f46e6574e4da65e1c6f5b64a0b71e574926a098df9952f9e9f40de0accdd4fb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "62916932a1509339e8b7735657c38c1a2dec3d6867ccbc31806aa29d57a6d97a", "generation_seconds_batch": 27.32812126900535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6112244129180908, "target_z": 0.3457031546917604, "ce": 6.133810997009277, "genuineness": 4.218649387359619, "identity": 0.6178662776947021, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/1f46e6574e4da65e1c6f5b64a0b71e574926a098df9952f9e9f40de0accdd4fb.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": "2037d5b4551038853abec94fb3f69c40ef6f6ecbb76b872f00ddcdf454f00fb6", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "590ad01ae79000a6250d5cac8e7f87883ca758743ccfb7444112b2d4bfd6d6b9", "generation_seconds_batch": 27.88847070094198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48104938864707947, "target_z": 0.15917969200380636, "ce": 6.292664527893066, "genuineness": 4.111956596374512, "identity": 0.2843790054321289, "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_Relief/2037d5b4551038853abec94fb3f69c40ef6f6ecbb76b872f00ddcdf454f00fb6.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "204ed0cb42ae4a7f3d1a7f14fa349c01f4a19880ab372266637e51deef7d660e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2a2cfa1312432bd4d8cd8b029ce196e0ec8e35c505352376d7bd8910bfc87f35", "generation_seconds_batch": 16.11930110596586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2205252647399902, "target_z": 1.2187500800676685, "ce": 6.252951145172119, "genuineness": 4.457139015197754, "identity": 0.7992618083953857, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/204ed0cb42ae4a7f3d1a7f14fa349c01f4a19880ab372266637e51deef7d660e.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "20626ba8710649331e7b4ebc9ec1dbf8be858f2f8f676c0566f280ef4d933028", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e3d456936ad45165dc3d4b9010e938cffb9bf8eec761b9decb14c8afe60475ab", "generation_seconds_batch": 27.853794640046544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27522292733192444, "target_z": -0.13574219867611206, "ce": 6.086154937744141, "genuineness": 4.444586753845215, "identity": 0.4084232747554779, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/20626ba8710649331e7b4ebc9ec1dbf8be858f2f8f676c0566f280ef4d933028.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": "20740efee255230cf33adc73b26592a5f11cf8d66b0ff42e7beee89ab53aef1d", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1c649d380bc9d10595c88b3610e482f53b02c549c9767e3f54f227e61e39081b", "generation_seconds_batch": 21.40804526908323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2391010820865631, "target_z": -0.18749998932431086, "ce": 6.23706579208374, "genuineness": 4.532451152801514, "identity": 0.5335683822631836, "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_Relief/20740efee255230cf33adc73b26592a5f11cf8d66b0ff42e7beee89ab53aef1d.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "207bb2c230bb6e28cc76a7d24b31c32a2297804c836abdd42950502aa5ea69b3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "f93546c44a579921fc7b9010aec24691652aa9be7151860620f1defda67b2b77", "generation_seconds_batch": 21.477924001053907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9969785809516907, "target_z": 0.8984374719763161, "ce": 6.213237762451172, "genuineness": 3.6914620399475098, "identity": 0.33369728922843933, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/207bb2c230bb6e28cc76a7d24b31c32a2297804c836abdd42950502aa5ea69b3.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "20d1ab1b6a6508d83319c1c0eea3104314e5cefc535e179c1666566cd424e7b0", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8dbad10b35fc76ca8d66afbd69507bc174f0149382145716ada10ada6ef365be", "generation_seconds_batch": 28.590444909990765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8824791312217712, "target_z": 0.734375018682456, "ce": 6.284721851348877, "genuineness": 4.2374773025512695, "identity": 0.5563791394233704, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/20d1ab1b6a6508d83319c1c0eea3104314e5cefc535e179c1666566cd424e7b0.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": "20e029804cb55dac9a60a075c414d82d4c1027d00bbe5f94ad3d9b77c01bd30f", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b33e8b59465604f8bf9d51533f6137148c2a082130284f13cd0907c38406da19", "generation_seconds_batch": 16.965002275072038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7011882662773132, "target_z": 0.474609367994079, "ce": 6.229123115539551, "genuineness": 3.9927117824554443, "identity": 0.5036666393280029, "hypothesis": "¿Tu mensaje llegó después de que me fuera? Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/20e029804cb55dac9a60a075c414d82d4c1027d00bbe5f94ad3d9b77c01bd30f.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "2145ae9a9de8201a7291ecd99fe339427225da179907d8913e8619f4f4d35fef", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "2a0e1f4fe096792ddf24ac4f1b96558efea3f118a52078a30ae96a3e9dede609", "generation_seconds_batch": 23.900935774086975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2859535217285156, "target_z": 1.3125000533784457, "ce": 6.268836498260498, "genuineness": 4.758388519287109, "identity": 0.45373302698135376, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2145ae9a9de8201a7291ecd99fe339427225da179907d8913e8619f4f4d35fef.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": "219d6ae2a36de372bbe6b71365f2b8f247c10b00daf382764f3264f30f7d370d", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b5412fab1db4294d3370e92c1a906f3572f830b45a40dce90b3aa771b42b16ff", "generation_seconds_batch": 18.704130155965686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4762785732746124, "target_z": 0.15234374933276942, "ce": 6.141753673553467, "genuineness": 4.457139015197754, "identity": 0.805988073348999, "hypothesis": "Quelqu'un a déplacé la petite chose bleue. Elle était ici, près de la grande bibliothèque. Nous la remettrons après le début.", "wer": 0.09523809523809523, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/219d6ae2a36de372bbe6b71365f2b8f247c10b00daf382764f3264f30f7d370d.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": "2220e7e16b3c441ecc5dd59344efefb1fedff53e44c2db089290c457d5d93442", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0d0e8e185f25563183d16a2aaf75d498d780ac166917393554f4f41287b3d124", "generation_seconds_batch": 21.267526806914248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7761582136154175, "target_z": 0.5820313120524431, "ce": 6.268836498260498, "genuineness": 4.20609712600708, "identity": 0.5609643459320068, "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_Relief/2220e7e16b3c441ecc5dd59344efefb1fedff53e44c2db089290c457d5d93442.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "231001e1d662c0cc9d00f6486f95496cf3a10cae1a22703e7b341f337501d6ee", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "9b654eb8c33d86ee2d5efed0c458de744e213fe30b3ffb8c6d8e84bd049344b9", "generation_seconds_batch": 24.716100166086107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3840959072113037, "target_z": 1.4531250133446114, "ce": 6.0146708488464355, "genuineness": 4.319066047668457, "identity": 0.5127905011177063, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/231001e1d662c0cc9d00f6486f95496cf3a10cae1a22703e7b341f337501d6ee.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "233af5ca5364c37fbc66de38cc81fd191d10c3ecf937c81c5fe1c94131773aab", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4c285a252289ce30dfaf3daa90ccb4ae5e505fd809e953e6acb41b5dac969c3e", "generation_seconds_batch": 21.32864022802096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7120929956436157, "target_z": 0.49023439201437957, "ce": 6.1894097328186035, "genuineness": 3.9927117824554443, "identity": 0.20266592502593994, "hypothesis": "The 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_Relief/233af5ca5364c37fbc66de38cc81fd191d10c3ecf937c81c5fe1c94131773aab.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "238a074ea85e7d2bec598f71e475d2c0b968b5f7fe563ec79368cb370191fc93", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab9c8369c56fc6ee8edcf1ebc6fae13894fbae568339875ee13a30b063a277e0", "generation_seconds_batch": 18.21022567700129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8497649431228638, "target_z": 0.6874999466215543, "ce": 6.23706579208374, "genuineness": 4.507347106933594, "identity": 0.7616896629333496, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/238a074ea85e7d2bec598f71e475d2c0b968b5f7fe563ec79368cb370191fc93.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "238a4d9477c96f4ebd1ce269e4cb12d29a822dcf0a1393f2b9af19a4c1d5f66b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "4f4436af1a332e391e23ae657b794774cfbbe37a5352cf29d95a7ba1bd9fd1d2", "generation_seconds_batch": 24.15843719500117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13278011977672577, "target_z": -0.33984376000845856, "ce": 6.1894097328186035, "genuineness": 4.250029563903809, "identity": 0.41303715109825134, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/238a4d9477c96f4ebd1ce269e4cb12d29a822dcf0a1393f2b9af19a4c1d5f66b.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "23b2b29294397e2c296b09c83502cd43bb388f53c41b8bcbdf6c69be17bfbc1d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f8990e6e84ac060cc6f7775ea7664734b9fc8be0a60d0967f0fde7a87f37e77c", "generation_seconds_batch": 24.398639764986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4851386547088623, "target_z": 0.16503906533572993, "ce": 6.308549880981445, "genuineness": 4.68307638168335, "identity": 0.6760146617889404, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/23b2b29294397e2c296b09c83502cd43bb388f53c41b8bcbdf6c69be17bfbc1d.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "23b30cb57bece4a1ba7f5c1a85dcff79a08c66f4d0f9deb1377bd0433e2442b8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "634b3819dbb6925dfcacffcf32c5c65c3e7d25a8afa2cb3848092bf26931f035", "generation_seconds_batch": 16.684013176942244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4626476764678955, "target_z": 0.13281249065877201, "ce": 6.292664527893066, "genuineness": 4.532451152801514, "identity": 0.7262356281280518, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/23b30cb57bece4a1ba7f5c1a85dcff79a08c66f4d0f9deb1377bd0433e2442b8.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "2421834548df64aa0f37f907d823e108ca46073a3c6d818703f9ff4e2a504076", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1a43ca2af40072b9f70852a4ddf929314d5b184532dbfe5407ec0dd03c8e9730", "generation_seconds_batch": 28.607052302919328, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2520504295825958, "target_z": -0.16894529998942678, "ce": 6.086154937744141, "genuineness": 4.293961524963379, "identity": 0.33333513140678406, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2421834548df64aa0f37f907d823e108ca46073a3c6d818703f9ff4e2a504076.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "2430fc6c85dd92342c8ffca6569c8fa513b9d8788c108fe89981156c93bffb4a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3836dd5a18f7e87ea2fce44c78088e4da9e852a3df732caf8dfc5749d06b62c7", "generation_seconds_batch": 24.524625450954773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4004528522491455, "target_z": 1.4765623358612796, "ce": 6.149696350097656, "genuineness": 4.344170093536377, "identity": 0.6009699106216431, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2430fc6c85dd92342c8ffca6569c8fa513b9d8788c108fe89981156c93bffb4a.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": "24642b06e24e98bde3c1e23dc3c530df694202c2d886809b30b0a1f6e00e09a0", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "927c991b347950d244e820163bbf1ba53584b1c57ff9141cd8194940662ed3a7", "generation_seconds_batch": 22.963121631997637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23978261649608612, "target_z": -0.18652344133657578, "ce": 6.308549880981445, "genuineness": 4.632867813110352, "identity": 0.5318015813827515, "hypothesis": "Je bericht kwam nadat ik vertrokken was. Ik las twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/24642b06e24e98bde3c1e23dc3c530df694202c2d886809b30b0a1f6e00e09a0.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": "24acf9fbb03ad0c4fda5638dcfbfb689a4131bdd86366e2ac110f278498c3a0b", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a20c8574de91c6ca742b331ab86a257ff2bf9989bae3134be8168f8b6d029a15", "generation_seconds_batch": 19.763028072891757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36484605073928833, "target_z": -0.007324205989215333, "ce": 6.24500846862793, "genuineness": 4.457139015197754, "identity": 0.4347801208496094, "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_Relief/24acf9fbb03ad0c4fda5638dcfbfb689a4131bdd86366e2ac110f278498c3a0b.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "26c7098a2f1b1dfc9accecd63f990893516b289da88c1c118f10f6f140ccb405", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ceaf3b535527f7f2911dafa65003e1c721be0bd07238486185586ee5afb9b69b", "generation_seconds_batch": 16.794014494051225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7148191928863525, "target_z": 0.49414066937083295, "ce": 6.038498878479004, "genuineness": 4.18099308013916, "identity": 0.47981366515159607, "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_Relief/26c7098a2f1b1dfc9accecd63f990893516b289da88c1c118f10f6f140ccb405.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "26c88345b710a4ea3e20f7e73e883920009f38483d206b0ef02ff6b3b4a83fbe", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "db2cb8ca33b3c0624365c8823d7c58f44c3f79567ee8de03cf9eac820449471c", "generation_seconds_batch": 24.41018462390639, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7270869612693787, "target_z": 0.5117187466638471, "ce": 5.685050010681152, "genuineness": 3.8546390533447266, "identity": 0.5644221305847168, "hypothesis": "La puerta sigue abierta ta sigue abierta, abierto sobre la silla. Dime cuándo estás listo.", "wer": 0.26666666666666666, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/26c88345b710a4ea3e20f7e73e883920009f38483d206b0ef02ff6b3b4a83fbe.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "c6de1d7a84ee1ea4940aeb91edfdc0f82e4ccc998b02bef324758d42ea96c4da", "generation_seconds_batch": 16.970057544996962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.41425803303718567, "target_z": 0.06347658001480248, "ce": 6.459460258483887, "genuineness": 4.3127899169921875, "identity": 0.19280044734477997, "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_Relief/26d12995a5b024b42cbe037fdee48ffb67b79df656c09f059592185aa881aca9.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "270f39f072ef25862a2a5ee766b4bdbc09693e3aec75359d96bf87cc41fb7474", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "e0bed42590f5a559ee523c67f49f1f12f38b2731bc8bd9e6dc71d8cc2489ac76", "generation_seconds_batch": 20.704614597023465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5267128944396973, "target_z": 0.22460941069683554, "ce": 6.372091293334961, "genuineness": 4.049196243286133, "identity": 0.4670732617378235, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/270f39f072ef25862a2a5ee766b4bdbc09693e3aec75359d96bf87cc41fb7474.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": "2713607763af3fa403a4c352c1c419694440b4b1a747bead4911f82c03ef2727", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "77acd71a52481ad567cb05c324f72fa5e24b0a777e379bc878dd218896919703", "generation_seconds_batch": 20.308469980955124, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2268332690000534, "target_z": -0.20507813067145986, "ce": 6.2767791748046875, "genuineness": 4.482243061065674, "identity": 0.7975115180015564, "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_Relief/2713607763af3fa403a4c352c1c419694440b4b1a747bead4911f82c03ef2727.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "271ffb1b6a862fb02a1d30b0066960d6dac3360c7303a59d971f8537b424660f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e10364c1ecf6dde92f1c9de13e9e6997bec5b002dcb12ee4ae9936f8cb41520d", "generation_seconds_batch": 24.449274851940572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0351450443267822, "target_z": 0.9531249279390983, "ce": 6.260893821716309, "genuineness": 4.444586753845215, "identity": 0.810576319694519, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/271ffb1b6a862fb02a1d30b0066960d6dac3360c7303a59d971f8537b424660f.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": "2739ee0b5704fe0d064c176e853e06fb6679de40df2952b8162e88d7a478d32a", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3ea2c89c6a7f549d571b5bc6f2d720effc18fd63574a51b310c64603ec1368e7", "generation_seconds_batch": 20.276618806063198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5485222935676575, "target_z": 0.25585937333192355, "ce": 6.292664527893066, "genuineness": 4.570107460021973, "identity": 0.6818491220474243, "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_Relief/2739ee0b5704fe0d064c176e853e06fb6679de40df2952b8162e88d7a478d32a.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "27527d24244de95452a8b30a09badb554cd41b224b061949c83506f0942fa191", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a697b322b30a8046026a8f6c12f1d2683a9dd0e860949271da4ffda7ef2ce369", "generation_seconds_batch": 18.076031811069697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5785102844238281, "target_z": 0.2988281680363718, "ce": 6.435632705688477, "genuineness": 4.3127899169921875, "identity": 0.5731760263442993, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/27527d24244de95452a8b30a09badb554cd41b224b061949c83506f0942fa191.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "27dd9bc4846196ece98c6abcbbeeda9278d3f1e1726cd76c462f6df8b46dab15", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "f93aca304eef8f1a360d7099f713c10937fb2841a8787a52404fbf387fdf16db", "generation_seconds_batch": 27.875174573040567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4531060457229614, "target_z": 0.11914060531669816, "ce": 6.372091293334961, "genuineness": 4.337893962860107, "identity": 0.46563902497291565, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/27dd9bc4846196ece98c6abcbbeeda9278d3f1e1726cd76c462f6df8b46dab15.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "282144eeafd8c2c99d4e16903b050dd88e8fd4b1c34147414dafa898b84298e3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8d39e3e26572ed0d62c546b797259edca0530405c499aa16d6d6c4c3f34c1972", "generation_seconds_batch": 24.406086859991774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7548561096191406, "target_z": 1.9843749759796994, "ce": 6.173524379730225, "genuineness": 4.331617832183838, "identity": 0.5024223923683167, "hypothesis": "J'ai trouvé la 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_Relief/282144eeafd8c2c99d4e16903b050dd88e8fd4b1c34147414dafa898b84298e3.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "284455b78dea9f6f83e8e42595a60e192ac206b293feb8c4db91e2f5d4b9ebba", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "218cb36e054d2b717c5c2374688c61b320d2e97ec2320181cbad1d115f583373", "generation_seconds_batch": 25.196564748999663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19888994097709656, "target_z": -0.24511719600718979, "ce": 6.109982967376709, "genuineness": 4.3127899169921875, "identity": 0.1171649694442749, "hypothesis": "De deur staat nog open? Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/284455b78dea9f6f83e8e42595a60e192ac206b293feb8c4db91e2f5d4b9ebba.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "2844d9ce39ed8d9e85a2f419626385b996f9e43f48658bb20bf53b43eeec229b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "def6397aa866e11fd0bc6f94b79a87be34d6a995b53189fa949d22cff8f7b884", "generation_seconds_batch": 24.136092718923464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2859535217285156, "target_z": 1.3125000533784457, "ce": 6.340320587158203, "genuineness": 4.306513786315918, "identity": 0.47347450256347656, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2844d9ce39ed8d9e85a2f419626385b996f9e43f48658bb20bf53b43eeec229b.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "284f6748e1cd03fe47f8c56be6e3932d419381bfba0883548f2e3091d364211f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "05a16cea955f1a6839bebf958a5d4721430eb43d59184d83b836de2b41885479", "generation_seconds_batch": 24.43107263208367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8824791312217712, "target_z": 0.734375018682456, "ce": 6.292664527893066, "genuineness": 4.532451152801514, "identity": 0.5598394870758057, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/284f6748e1cd03fe47f8c56be6e3932d419381bfba0883548f2e3091d364211f.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "28988a8abfa67ba7d0313975020fac72a190d33271014244a578f4a0f6cac9d3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4047b00e166762629fad3a36d9ec5cb00132ffadf6d4c47750b02c634b715d33", "generation_seconds_batch": 24.41018462390639, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6044089794158936, "target_z": 0.33593754670613996, "ce": 6.022613525390625, "genuineness": 4.18726921081543, "identity": 0.5864840745925903, "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_Relief/28988a8abfa67ba7d0313975020fac72a190d33271014244a578f4a0f6cac9d3.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "28a70dede3caa8ba330b83abc8d9658f038cfa0f6f64f581847d4ab99f699f3e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "d1525d3f0ac3e0657cd5234452e8760832447ffc5151ca9f1de2de57f480686e", "generation_seconds_batch": 22.998699732939713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9124670624732971, "target_z": 0.7773437279813912, "ce": 6.078212261199951, "genuineness": 4.532451152801514, "identity": 0.5846232771873474, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/28a70dede3caa8ba330b83abc8d9658f038cfa0f6f64f581847d4ab99f699f3e.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "29b5770c3224bfe394ee50fef9522c84e27e200a466e94ca1e0eab8eef074323", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "736f15ebdab40d7bb5415c03b9e98b7889f3a3d22b6d08ddcc2c2efc65ae532d", "generation_seconds_batch": 24.464805445051752, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9015623927116394, "target_z": 0.7617187893666036, "ce": 6.086154937744141, "genuineness": 4.457139015197754, "identity": 0.7068371772766113, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/29b5770c3224bfe394ee50fef9522c84e27e200a466e94ca1e0eab8eef074323.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "29c384cbf87394f415faec58b3d74202dcfd63eb4f47cc5646f499ae20f6896e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ed8dfaef4cd0c1f7f2c69006d49c6863cb5bfab70d01973e55ffd8e1bcc41dc0", "generation_seconds_batch": 15.99066079291515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7243608236312866, "target_z": 0.5078125547129068, "ce": 6.09409761428833, "genuineness": 3.810706615447998, "identity": 0.43140822649002075, "hypothesis": "The 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_Relief/29c384cbf87394f415faec58b3d74202dcfd63eb4f47cc5646f499ae20f6896e.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "2a5b0abf30636a2632cc0dd844346d4184958fb9c95ae7e88d9cc0f7873bea0e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "85ed30d5ae30568893ad82a32cdb5b1fb7a6ad68117567351c8d558100d3673c", "generation_seconds_batch": 24.339464670047164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7080037593841553, "target_z": 0.4843750613852125, "ce": 6.1020402908325195, "genuineness": 4.400654315948486, "identity": 0.5670344829559326, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2a5b0abf30636a2632cc0dd844346d4184958fb9c95ae7e88d9cc0f7873bea0e.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "2a7cb963f5830a8d93c8de8972ab6949395670b7d7064f6c3be9fa9fe2c58cf0", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "51419a567c55617613008bfd65f6cef3d77a2d6693a9059df0ca1fac38f54906", "generation_seconds_batch": 24.832501029013656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.231429934501648, "target_z": 1.234375018682456, "ce": 5.959072113037109, "genuineness": 4.287685871124268, "identity": 0.6790638566017151, "hypothesis": "J'ai trouvé la petite boîte. Elle était prêt de la vie fenêtre. We've regarded ensemble what.", "wer": 0.42105263157894735, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2a7cb963f5830a8d93c8de8972ab6949395670b7d7064f6c3be9fa9fe2c58cf0.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "2aff8eab4d197d6a2da1d56b4ad0e7714ca18db7d1539ea846b7f5103ed92c3c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cdfb323a45d19a4639831b11034443ef9426c5170a0113c1831139e8298ef57f", "generation_seconds_batch": 25.265932149020955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9015623927116394, "target_z": 0.7617187893666036, "ce": 6.205295085906982, "genuineness": 4.494794845581055, "identity": 0.4681824743747711, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2aff8eab4d197d6a2da1d56b4ad0e7714ca18db7d1539ea846b7f5103ed92c3c.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "2b3d98b154f20ebc865fd99cbe3acf0d9ac8b7035b16a0a3d7d48c7b1811de48", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "32e9a2c4f207aa4e854a0717c1510360815c4f9975af320d1c50e8c11702cd6e", "generation_seconds_batch": 24.771130832028575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3186676502227783, "target_z": 1.3593750400338342, "ce": 6.213237762451172, "genuineness": 4.482243061065674, "identity": 0.5697461366653442, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2b3d98b154f20ebc865fd99cbe3acf0d9ac8b7035b16a0a3d7d48c7b1811de48.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "2b756a144c49dae13f9ec04bb4c79433f05fc5b9be70ea41281f200981e70d0c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "987c9b1056b107dfb65ab4522de30a68cc14eee38673f2a0f168340203c86389", "generation_seconds_batch": 18.550674095051363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29226154088974, "target_z": -0.11132813600930441, "ce": 6.070269584655762, "genuineness": 4.319066047668457, "identity": 0.5360665321350098, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2b756a144c49dae13f9ec04bb4c79433f05fc5b9be70ea41281f200981e70d0c.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": "2b95e0a9bdee27f923293bf2fe0899ff910a1733a6abd571d4b276762e086590", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e602b2c5a6a473228f5a9065692c778c4a30fba4282f1df2ea28458aa0e77f39", "generation_seconds_batch": 22.963121631997637, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7134560346603394, "target_z": 0.4921874452870932, "ce": 6.23706579208374, "genuineness": 4.375550270080566, "identity": 0.7361592650413513, "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_Relief/2b95e0a9bdee27f923293bf2fe0899ff910a1733a6abd571d4b276762e086590.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "2bd15256352e2fccb7da42fbf769cb60c9b4a069d68e5483b92b6c065abcb532", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4a79118d73db8d068be2f3de8aead7a50b0d5715961e6201141dac6ae148219d", "generation_seconds_batch": 25.70037372491788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6493908762931824, "target_z": 0.40039061065454273, "ce": 6.062326908111572, "genuineness": 4.042920112609863, "identity": 0.7619843482971191, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2bd15256352e2fccb7da42fbf769cb60c9b4a069d68e5483b92b6c065abcb532.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "2bf6d08ecf2f7edcfae2988a9d9170bb7a3504d44ba6acc3a24cd021bd7ab800", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6ea40e96f889a3151295b151ecdb5b6153137e6440f525bbdaca2fab372c9fe8", "generation_seconds_batch": 20.886213725083508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9838550090789795, "target_z": 2.3124998825674195, "ce": 6.348263263702393, "genuineness": 4.394378662109375, "identity": 0.3495236337184906, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2bf6d08ecf2f7edcfae2988a9d9170bb7a3504d44ba6acc3a24cd021bd7ab800.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "2c11983457ccf42e4e228bd9a884acd89e7bc46d3b32f4b7e8d1447b79e054f1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0cbb05e1d31059a54c117467e71ca69a054108d93d50996537b9680431ef476e", "generation_seconds_batch": 25.789295181981288, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3041885793209076, "target_z": -0.09423827933171211, "ce": 6.332377910614014, "genuineness": 4.570107460021973, "identity": 0.5617581009864807, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2c11983457ccf42e4e228bd9a884acd89e7bc46d3b32f4b7e8d1447b79e054f1.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "2c1203a225c93279c165e6022b7ee362b97054c5db044c9a4a9f0fa5ca18040f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f013be75251b9ce2acce286fc1dce99c5376ea1c4cfe1f50fad5c3af98cf7a18", "generation_seconds_batch": 24.20875903603155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.814324676990509, "target_z": 0.6367187680152254, "ce": 6.2767791748046875, "genuineness": 4.319066047668457, "identity": 0.7803120613098145, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2c1203a225c93279c165e6022b7ee362b97054c5db044c9a4a9f0fa5ca18040f.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "2c4871cb789b444e4f0f6caa1c66b8c6ebc2840602f28ca8c1c7be2743aabf54", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "22bcf92065bff23808285a8dcad76cbc389bf698ca67ca94794a38917613055b", "generation_seconds_batch": 18.94264407805167, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7816104888916016, "target_z": 0.5898436959543237, "ce": 6.046441555023193, "genuineness": 4.080576419830322, "identity": 0.5638176202774048, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2c4871cb789b444e4f0f6caa1c66b8c6ebc2840602f28ca8c1c7be2743aabf54.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "2c55661133955cc654f9e7e2f553215f5a620aaad4f891d34aedebc816c184e9", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4bd66fdc931e994593cedc034c48276f09107972667c99498b24b8e10a3eb292", "generation_seconds_batch": 21.927426425972953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7166895866394043, "target_z": 1.9296874346114041, "ce": 6.23706579208374, "genuineness": 4.268857479095459, "identity": 0.6727719306945801, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We'll regard ensemble what it contiens?", "wer": 0.3157894736842105, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2c55661133955cc654f9e7e2f553215f5a620aaad4f891d34aedebc816c184e9.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "2c88449af62496ebc97ed9061501f81f7f2cda2a866cec2d47745907a72d68d3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "05de942bd20be905548094d70e3d478453ca0607a1fa41be8fff730583d7d40b", "generation_seconds_batch": 17.252934913965873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8334078788757324, "target_z": 0.66406245329386, "ce": 5.9431867599487305, "genuineness": 4.231201171875, "identity": 0.5195653438568115, "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_Relief/2c88449af62496ebc97ed9061501f81f7f2cda2a866cec2d47745907a72d68d3.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "2cd096cd18eff9a975a5702b0820186bdcbc6865ea8a2e85ab963c046e3de985", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e8eefc134111abd32fd6f642588ff732a19aa79c91cbd93e919adb6b546ffb35", "generation_seconds_batch": 21.097281535039656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19957149028778076, "target_z": -0.24414062666807643, "ce": 6.070269584655762, "genuineness": 4.331617832183838, "identity": 0.8496373891830444, "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_Relief/2cd096cd18eff9a975a5702b0820186bdcbc6865ea8a2e85ab963c046e3de985.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "2d84ec4479fa6faa24ef13d297d907f238a188bf87c931006afe6d67caad8919", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ff072cd32df78f3e252bae9af5d5bcd4a6db24f71f498a40d48b735b6ddb5fc1", "generation_seconds_batch": 25.129970162990503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4541283845901489, "target_z": 0.12060548067674645, "ce": 6.229123115539551, "genuineness": 4.469690799713135, "identity": 0.5015497207641602, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2d84ec4479fa6faa24ef13d297d907f238a188bf87c931006afe6d67caad8919.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "2e18b3884df8cd3773cffbe8f3de3c0b85332fc99d400d7765809f5528ced332", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "251270dc6ddec14c0531f70a63127f310a60a394afc674155ddf12d66bf5793d", "generation_seconds_batch": 22.226476851967163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.607642412185669, "target_z": 1.7734373652194246, "ce": 6.1894097328186035, "genuineness": 4.1998209953308105, "identity": 0.5940879583358765, "hypothesis": "I've tried the petite boîte. It is pretty fenêtre. We've got.", "wer": 0.8421052631578947, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2e18b3884df8cd3773cffbe8f3de3c0b85332fc99d400d7765809f5528ced332.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "2eac5574b30fb64b9ba87ee61a8e9a59071a302fea8a408ac63f1cdfa6aeef71", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "4138e5ac182e938783b83272a39e59d0aab00cd88c23a9e1f5cc868fd91d5cae", "generation_seconds_batch": 23.666474730009213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1332874298095703, "target_z": 1.093749887905264, "ce": 5.824047088623047, "genuineness": 4.093128204345703, "identity": 0.5480610132217407, "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_Relief/2eac5574b30fb64b9ba87ee61a8e9a59071a302fea8a408ac63f1cdfa6aeef71.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": "2ed792ba81428762a9a57a0d6b46290b119b0aa1502097661e4c34d5adbde92f", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f68b526950d949e1ae69b21fed7eb0f078d0c12da37033eb2e0fa923ca685294", "generation_seconds_batch": 23.44592399604153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28749072551727295, "target_z": -0.11816407868034134, "ce": 6.23706579208374, "genuineness": 4.425758361816406, "identity": 0.8374695181846619, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de laar en daarna, naast het raam, neem ze mee als je weggaat.", "wer": 0.045454545454545456, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/2ed792ba81428762a9a57a0d6b46290b119b0aa1502097661e4c34d5adbde92f.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "30201aa7f6465fc38112496c4ca59972a2e200822adbccb7b0f3088eb1e77da5", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "44b8d513c307a9f110c7ed35df5899c82d230dfdf887acd9d71a95137e119392", "generation_seconds_batch": 24.347462904988788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2718152105808258, "target_z": -0.14062500266892228, "ce": 6.133810997009277, "genuineness": 4.3504462242126465, "identity": 0.6987019181251526, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/30201aa7f6465fc38112496c4ca59972a2e200822adbccb7b0f3088eb1e77da5.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "306243c5c43b9dc220e2f41ec9ad77399f6292dc729dc7111517e2c3fce5eee1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "30ef101e388b3e2a762c6b266864b7da24d9811e8d908c17b51b2e17e682bab9", "generation_seconds_batch": 26.94112716394011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9424550533294678, "target_z": 0.8203125226858394, "ce": 6.141753673553467, "genuineness": 3.8169827461242676, "identity": 0.2952784597873688, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/306243c5c43b9dc220e2f41ec9ad77399f6292dc729dc7111517e2c3fce5eee1.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": "306814496f29bedd01a3278afd9d0bcc30f719c707a31cb1697ef6511053e2a1", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e2806acbb429df1eb5d2ddefbae8539eb332a76975bf1865adb4b841522f36bb", "generation_seconds_batch": 20.276618806063198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8743005990982056, "target_z": 0.7226562720186088, "ce": 6.197352409362793, "genuineness": 4.319066047668457, "identity": 0.6586012244224548, "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_Relief/306814496f29bedd01a3278afd9d0bcc30f719c707a31cb1697ef6511053e2a1.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "306e1590cc9e92719f7d862bef194d3bd5fa0f74eed68c40237d09806dada8cc", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2187b50e5316c34fb16f19251ae105f06fe55a1a215f71ba2dac09e82aa6e350", "generation_seconds_batch": 22.991053901962005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.138739824295044, "target_z": 1.101562442618171, "ce": 5.6413655281066895, "genuineness": 4.036643981933594, "identity": 0.5426815748214722, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lenta.", "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_Relief/306e1590cc9e92719f7d862bef194d3bd5fa0f74eed68c40237d09806dada8cc.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "30b167a8ab669f182d41c170f3e336ef63fb0af239a333bc585b1f66d8316867", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "95a0bd1b9721a0752526e15188000a50056ceca6cf1828fca20d0f030f5ce32c", "generation_seconds_batch": 24.85053160006646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43334126472473145, "target_z": 0.09082030799619364, "ce": 6.38797664642334, "genuineness": 4.331617832183838, "identity": 0.5420539379119873, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/30b167a8ab669f182d41c170f3e336ef63fb0af239a333bc585b1f66d8316867.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "31361bd090581974dbf3320b571fd1608695623bfd6d02d0d9e1f9439194f442", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1deda5c2476e19c535190e8f39a35c7297e6a3b74d14ebf90f6fa6721a130d26", "generation_seconds_batch": 18.49285354395397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18730369210243225, "target_z": -0.26171874666384715, "ce": 5.959072113037109, "genuineness": 4.137060642242432, "identity": 0.2454453706741333, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/31361bd090581974dbf3320b571fd1608695623bfd6d02d0d9e1f9439194f442.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "31c10fb5188bbd59a0aff9ccfb5c757cc330a941f96ca8f78c50deda30e2948f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "94e57941119ecd8d7081ef03bf3e6dd2248a30cf16af047974086198bb4cdf6f", "generation_seconds_batch": 21.509229005896486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.07553038001060486, "target_z": -0.42187500800676686, "ce": 5.982900142669678, "genuineness": 4.262581825256348, "identity": 0.6189552545547485, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/31c10fb5188bbd59a0aff9ccfb5c757cc330a941f96ca8f78c50deda30e2948f.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "32300432199a0164a57ea80736b9aba6fb3cf1529c078c0f45153589147b7b8b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bbd8d4fe31086b2a2a5a2ddd6f730b0a807190b6093c16acec5f7badcbfb766a", "generation_seconds_batch": 24.144749078084715, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.08966863155365, "target_z": 1.031249962635088, "ce": 5.95112943649292, "genuineness": 3.9676074981689453, "identity": 0.49501240253448486, "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_Relief/32300432199a0164a57ea80736b9aba6fb3cf1529c078c0f45153589147b7b8b.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "324c277701fb39180e6d0c932e56527d5bf67c8be7d32c86431b7fc5d14e1836", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9366a70dac29fca8aa405097c6956a984efdd1733acb381eee6b022badd2488a", "generation_seconds_batch": 21.12887838797178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7025513648986816, "target_z": 0.4765625066723057, "ce": 6.24500846862793, "genuineness": 4.068024158477783, "identity": 0.5556745529174805, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/324c277701fb39180e6d0c932e56527d5bf67c8be7d32c86431b7fc5d14e1836.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "32a90afc6a0d6b0f82c4c230927282d9d20f0be9203d70b88a9d1a7d2eff329c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "dcc19b0e1896d007bd468e30b6365d5342f0df86ecb7e71cb5658d56c133f680", "generation_seconds_batch": 24.943288597045466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7161822319030762, "target_z": 0.4960937226435466, "ce": 6.300607204437256, "genuineness": 4.21237325668335, "identity": 0.31452399492263794, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/32a90afc6a0d6b0f82c4c230927282d9d20f0be9203d70b88a9d1a7d2eff329c.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": "334e84ce2d56b538223ea9694da85172a03738c8887d156901ae1ef2b72af18d", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "085a31e7ca868f4ad91a2f7da7f0d42c78cbd55edd9d47a4e09c0b07b768cbdc", "generation_seconds_batch": 21.785958433058113, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43640822172164917, "target_z": 0.09521484867082546, "ce": 6.229123115539551, "genuineness": 4.293961524963379, "identity": 0.22576503455638885, "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_Relief/334e84ce2d56b538223ea9694da85172a03738c8887d156901ae1ef2b72af18d.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "3356fc17920bbb08516a00eac53bbc392f33d5a6673d6b72cf793918b893755e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fc04d082f977295a64d178346cfba86c0586bbf78bdb5782b01dd09c3c359571", "generation_seconds_batch": 21.57926731801126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9370026588439941, "target_z": 0.8124999679729326, "ce": 6.1020402908325195, "genuineness": 4.143336772918701, "identity": 0.6015522480010986, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3356fc17920bbb08516a00eac53bbc392f33d5a6673d6b72cf793918b893755e.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "335b1830e67e5fb3c2d778edf64f0fd9036c5c37f4a0cf704e7d1b65b3fcb71d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e47f02662f7e5a558be6520fc05c7a723ca8dc28a687b48262b5a58525f4f398", "generation_seconds_batch": 30.001967835938558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.305551677942276, "target_z": -0.0922851406534854, "ce": 6.24500846862793, "genuineness": 4.482243061065674, "identity": 0.468474417924881, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/335b1830e67e5fb3c2d778edf64f0fd9036c5c37f4a0cf704e7d1b65b3fcb71d.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": "338f6fa7ff74a004948bae05bbbcffdeb7f63c05cb736ed28279c33397c1fc84", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "878e2f8a200b1fe5c3f2c8e06a73a1ec9b375436b495acc4d14d2c0e3ca67509", "generation_seconds_batch": 23.44592399604153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3984121084213257, "target_z": 0.0407714816643758, "ce": 6.23706579208374, "genuineness": 4.369274139404297, "identity": 0.6626785397529602, "hypothesis": "De sleutels liggen op de keukentafel. Ik keek in de la en daarna naast het raam. Neem ze mee je 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_Relief/338f6fa7ff74a004948bae05bbbcffdeb7f63c05cb736ed28279c33397c1fc84.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "d2beaaa731a4f4933f8cb234cffd580abaacf51d143b4c1495c3f51548a8b89e", "generation_seconds_batch": 19.387738354038447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15731573104858398, "target_z": -0.30468749866553885, "ce": 6.0305562019348145, "genuineness": 4.362998008728027, "identity": 0.23750294744968414, "hypothesis": "De weg gaat linksaf naar de brug. Loopt verder tot aan het kleine houten hek. Ik wacht aan de andere kant.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/33f63538ac2c49676cc53462aa2024b47e58cb29b8690774a6580785ecb0e60e.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "34151f6eba5de946fedf4f319b4af64cfc2517e1715c5ca6d37357f6e742ddc6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "cff14ab121b1bf4e8063276f431de6d5a9500b1a4591b3f886eee04b2a93ee18", "generation_seconds_batch": 23.585255458019674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4145987927913666, "target_z": 0.06396484333298089, "ce": 6.23706579208374, "genuineness": 4.375550270080566, "identity": 0.4993852376937866, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/34151f6eba5de946fedf4f319b4af64cfc2517e1715c5ca6d37357f6e742ddc6.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "342a463c936417755dc484e4cb57c8264a7ec57bc8367393ac786789965d2534", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "85143773bd6c5cbb07468040a2091889a3bd0e899297d972e44f1e74995d12f5", "generation_seconds_batch": 15.793477678089403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1441922187805176, "target_z": 1.1093749973310778, "ce": 6.340320587158203, "genuineness": 4.394378662109375, "identity": 0.45444875955581665, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/342a463c936417755dc484e4cb57c8264a7ec57bc8367393ac786789965d2534.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "343f8ae5658b01815f83da085eda666a0ed5c750fa075eaa5ccc812c87878163", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ac51ffdd0933cae5f07642f2a1d8ca54edb0615c132c9bedf81dab4d52e31709", "generation_seconds_batch": 24.07032531197183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5403437614440918, "target_z": 0.24414062666807643, "ce": 6.24500846862793, "genuineness": 4.080576419830322, "identity": 0.34129786491394043, "hypothesis": "The 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_Relief/343f8ae5658b01815f83da085eda666a0ed5c750fa075eaa5ccc812c87878163.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "34435f071a4bb344d4afb839dc12c8bd16c4f952101fb2c8ed8651a7b03756ff", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "1b8dde76d679d249083e60a880bba73960dc687aa4116534bcdf38582d85f678", "generation_seconds_batch": 17.83869888400659, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5144450664520264, "target_z": 0.2070312479983083, "ce": 6.395919322967529, "genuineness": 4.231201171875, "identity": 0.41358840465545654, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/34435f071a4bb344d4afb839dc12c8bd16c4f952101fb2c8ed8651a7b03756ff.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "6cd875628ca9bc1244836d38c2ecc43b58f22aa166ba7b90f676897551cb9e4d", "generation_seconds_batch": 17.663099194993265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21183928847312927, "target_z": -0.2265625066723057, "ce": 6.419747352600098, "genuineness": 4.118232727050781, "identity": 0.3587462604045868, "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_Relief/347b084eb1c87968a3fc14b855043a2de140e81cf0874b7d65525285bfb31414.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": "349aa55665113f5879ee7a1ff11c130ad2dda8c2995bcbd67e9d50923a47808c", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6bbaafce19f491905249de401223c85005a27c6834dc0eba07fb59daa6ab041e", "generation_seconds_batch": 16.006637098966166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.473552405834198, "target_z": 0.14843751467907257, "ce": 6.38003396987915, "genuineness": 4.193545341491699, "identity": 0.24656321108341217, "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_Relief/349aa55665113f5879ee7a1ff11c130ad2dda8c2995bcbd67e9d50923a47808c.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "34ef2827e3ff7799d0cbf88fe6d6ac9288400f4c3126b6f2a84d76fbd1571428", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2645e540044c06719bcf28d417cf22dff3e7c33bbbe3328c60c225c4b391bc64", "generation_seconds_batch": 27.075846263905987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7093667984008789, "target_z": 0.48632811465792614, "ce": 6.125868320465088, "genuineness": 4.519899368286133, "identity": 0.6180053949356079, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/34ef2827e3ff7799d0cbf88fe6d6ac9288400f4c3126b6f2a84d76fbd1571428.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "350db371626d0b9f80f590594ba42008d5ee45d0334ddfeb0b36243ce0532b29", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a8f50ae5b87296af9be50661f474c8d1a7e338775584bda92df65eff902ca6eb", "generation_seconds_batch": 20.944683080073446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.329572319984436, "target_z": 1.3749999786486218, "ce": 6.197352409362793, "genuineness": 4.3504462242126465, "identity": 0.37784162163734436, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/350db371626d0b9f80f590594ba42008d5ee45d0334ddfeb0b36243ce0532b29.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "35579e37f896adb013b6b53e6cfb1c724683a9e00e5bb5367c3ce3ff4f13ce7c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "fa5ddae1193253c26e655c0524cbcf271fc8a2b886a09b49ef781ad760613874", "generation_seconds_batch": 29.7563175780233, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6185472011566162, "target_z": 1.7890624746452384, "ce": 6.173524379730225, "genuineness": 4.2249250411987305, "identity": 0.38325828313827515, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/35579e37f896adb013b6b53e6cfb1c724683a9e00e5bb5367c3ce3ff4f13ce7c.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "3571eafab2b0db8c2c3fbd87c04cb5aafa5022e9092a7d9407a450e0404f175d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7e15d222d133a70eaf0ef0ca59064f0a18753fc92e9a0cdebe59fab19bcdf535", "generation_seconds_batch": 23.088153496966697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2854461073875427, "target_z": -0.12109374399492487, "ce": 6.006728172302246, "genuineness": 4.381826400756836, "identity": 0.25276145339012146, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3571eafab2b0db8c2c3fbd87c04cb5aafa5022e9092a7d9407a450e0404f175d.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "37063e939a6be5962353ac26f37f8b45b9cd6d2e350d52068db43e4a242ffed0", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "343d7917615041d73220bb16099bddd1feb0de2913f2492e83f7d53d8de5e633", "generation_seconds_batch": 24.257414555060677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.35394132137298584, "target_z": -0.022949230009515882, "ce": 6.340320587158203, "genuineness": 4.413206577301025, "identity": 0.5426099896430969, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/37063e939a6be5962353ac26f37f8b45b9cd6d2e350d52068db43e4a242ffed0.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "3771d3e824bac86471ec9a176795f30367f3a4c0f5b21f610df7df01c0a0a07f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bd69502bc42046e5dad05addd7d0562632c2aa4a3bb65e98cd472ad0028a39ee", "generation_seconds_batch": 25.32129802601412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7298130989074707, "target_z": 0.5156249386147875, "ce": 6.141753673553467, "genuineness": 3.6349775791168213, "identity": 0.09124445170164108, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3771d3e824bac86471ec9a176795f30367f3a4c0f5b21f610df7df01c0a0a07f.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "385925470ee242ff01151beb58cdff6f8be0349f7da54a74319c1f0ec907da72", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "87b86707190cbfe865f28ecb04383e993984ce7490ea961abaa0925bdc822ec2", "generation_seconds_batch": 24.741545588010922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28817227482795715, "target_z": -0.11718750934122799, "ce": 6.006728172302246, "genuineness": 4.143336772918701, "identity": 0.46760356426239014, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/385925470ee242ff01151beb58cdff6f8be0349f7da54a74319c1f0ec907da72.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "38963b5495c1552777875781fdd16b77ee759078e54979195bf2f9eedc91cf82", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ce141a91ed4b219d9b48e0f70512346b910d24faa15e6019c85c391dcf785918", "generation_seconds_batch": 25.869001772953197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.820284366607666, "target_z": 2.0781249492904768, "ce": 6.165581703186035, "genuineness": 4.344170093536377, "identity": 0.42895933985710144, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/38963b5495c1552777875781fdd16b77ee759078e54979195bf2f9eedc91cf82.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "38a9ecca45cdb9710a527a11f6443db5183ba6328f81d4352cc05262e0709ce3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "90747b298bc1a451445290e938a45056c949c7975e383c7477c146d49b543d65", "generation_seconds_batch": 24.876981231034733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3677388429641724, "target_z": 1.4296875200169172, "ce": 6.062326908111572, "genuineness": 3.961331605911255, "identity": 0.24543750286102295, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/38a9ecca45cdb9710a527a11f6443db5183ba6328f81d4352cc05262e0709ce3.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": "38b2e83a95da1bac7bd1cdc5562b820497828f7d89777bf8d618d7bac485f125", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5fb1c0deca95b11a6b478e689ab241dc195895806acf4113521adb0fce6d6c5f", "generation_seconds_batch": 18.855725826928392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2423346042633057, "target_z": 1.2499999572972436, "ce": 6.141753673553467, "genuineness": 4.243753433227539, "identity": 0.5712563991546631, "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_Relief/38b2e83a95da1bac7bd1cdc5562b820497828f7d89777bf8d618d7bac485f125.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "38be330bb938d089bbe4608b00131e3efa240526f1fd6db3780fd0d1427ecf43", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "a0aa57dfe99296305d564163853ceb68aaa98920b0ff87a9568a9bf93e9ed96d", "generation_seconds_batch": 18.076031811069697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.718908429145813, "target_z": 0.5, "ce": 6.427689552307129, "genuineness": 4.193545341491699, "identity": 0.33601096272468567, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/38be330bb938d089bbe4608b00131e3efa240526f1fd6db3780fd0d1427ecf43.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "38c1369ea24ccc79595eed910d6b11e284aeb0d731a67d2e807e7edeca6fc6ab", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "af325f986aac5fa3e5ed29b673426eb64148f968cbd9da595ed7f1289ed5f276", "generation_seconds_batch": 28.154039929038845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4549765586853027, "target_z": 1.5546875413682955, "ce": 6.038498878479004, "genuineness": 4.18099308013916, "identity": 0.6299117803573608, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/38c1369ea24ccc79595eed910d6b11e284aeb0d731a67d2e807e7edeca6fc6ab.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "38f1b7ac97bd3589ea7e9599ad1e2c5d5a108e13f07aeeae2e831c34a2df299e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "9eb496d689c3b127e58b0407255e6d0d6b01176de6b7536275bb2949bd7c384c", "generation_seconds_batch": 27.027711601927876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.166001558303833, "target_z": 1.1406248745606526, "ce": 6.165581703186035, "genuineness": 4.042920112609863, "identity": 0.3825533390045166, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/38f1b7ac97bd3589ea7e9599ad1e2c5d5a108e13f07aeeae2e831c34a2df299e.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "390e80c947db0f045ca7369382e2a9e5bcd14b99e6bfbd8966c8efabf9c1c4cd", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e8429035bf3e9fda2a4f80cd79dc2c84a79dd16c0a13d8b21ab41ce5dd15fde", "generation_seconds_batch": 21.831020062905736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9533597230911255, "target_z": 0.8359374613006268, "ce": 6.09409761428833, "genuineness": 4.494794845581055, "identity": 0.6251544952392578, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/390e80c947db0f045ca7369382e2a9e5bcd14b99e6bfbd8966c8efabf9c1c4cd.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "3910779cc3490fca59349969a5c69d3cc53d26dea488415007349f7f325619db", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b2c8ed7b7abe2a3de81db59ce7e0fe424fba1791e62924ac6dd159a37c7da774", "generation_seconds_batch": 25.94559709506575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3000917434692383, "target_z": 2.765624981317544, "ce": 6.006728172302246, "genuineness": 4.030367851257324, "identity": 0.5044666528701782, "hypothesis": "I've tried the petite boat. It is pretty fenêtre.", "wer": 0.8947368421052632, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3910779cc3490fca59349969a5c69d3cc53d26dea488415007349f7f325619db.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "3917f5b2501ed43a0bccb7c78ed56b228809b2fdd2846af631aea4be41a81bbb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4adf5724b49d5349421f3f318d13421eba4505379da390ee1110848a5f3ca123", "generation_seconds_batch": 23.341405760962516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5117188692092896, "target_z": 0.2031249706418549, "ce": 6.38003396987915, "genuineness": 4.193545341491699, "identity": 0.34517109394073486, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3917f5b2501ed43a0bccb7c78ed56b228809b2fdd2846af631aea4be41a81bbb.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "3923a966c2789c93a3bf5efe80bac63e9e02deaef2975d3a738797d9bbd7e615", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": 129, "seconds_generated": 10.32, "mp3_sha256": "3ca26d87b001b875c7afb3cbec26a8740a8a9329124528df3e4bf2fab2385497", "generation_seconds_batch": 25.6094871989917, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2259775400161743, "target_z": 1.2265624639695492, "ce": 6.260893821716309, "genuineness": 4.20609712600708, "identity": 0.6756638884544373, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hinein.", "wer": 0.0625, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3923a966c2789c93a3bf5efe80bac63e9e02deaef2975d3a738797d9bbd7e615.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "394ae8408e9d5f49dbca8ca9c2de213649660d6f412169ff166235912d859ea4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "cb23de646275ef0264704ed1ccd9acc37554578a1b5cca8e74db8ed18b8c4f25", "generation_seconds_batch": 27.128995870938525, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.209620475769043, "target_z": 1.203124970641855, "ce": 6.332377910614014, "genuineness": 4.457139015197754, "identity": 0.8264883160591125, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/394ae8408e9d5f49dbca8ca9c2de213649660d6f412169ff166235912d859ea4.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "3968b8d60732cb7d0484e10cdc40c6bcf0acd69bda48b134f9ad66cfb3abe90a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dcb863e14bc18de077902fdf1733fe5e10c6c43365172fdeb20838d81036fb59", "generation_seconds_batch": 17.347004293929785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.209620475769043, "target_z": 1.203124970641855, "ce": 6.340320587158203, "genuineness": 3.9048471450805664, "identity": 0.28601768612861633, "hypothesis": "The 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_Relief/3968b8d60732cb7d0484e10cdc40c6bcf0acd69bda48b134f9ad66cfb3abe90a.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "397fd39660cc5e4f5f8c629784e115daa74fd034e20a3e72b9a39531dd3bf4a8", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "15e3257c68c7bfa717603a1a9f18658a21b8dd0c5d3468a17d27819c1e366ffd", "generation_seconds_batch": 17.520369679899886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.231429934501648, "target_z": 1.234375018682456, "ce": 6.403861999511719, "genuineness": 4.545003414154053, "identity": 0.5595136880874634, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/397fd39660cc5e4f5f8c629784e115daa74fd034e20a3e72b9a39531dd3bf4a8.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "398eaa7131572c32080f291b79b7bfb321037583ed0a98eb9edb16b5b7bab82d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af82e64105c16b2722192e3c89682c18f4d313fd63c2db52777eb6b33a21fdc4", "generation_seconds_batch": 28.30075575201772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2152470201253891, "target_z": -0.22167968132811722, "ce": 6.292664527893066, "genuineness": 4.482243061065674, "identity": 0.7762219309806824, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/398eaa7131572c32080f291b79b7bfb321037583ed0a98eb9edb16b5b7bab82d.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "399873a564d9997731fec6a6b75f787f41001e142cd683b3919e7a24852b4201", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5cc19d18c5e8a347df97971d4291f197b280a8d59a5b7082a95e765d52517038", "generation_seconds_batch": 18.21022567700129, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2750487327575684, "target_z": 1.2968749439526321, "ce": 6.300607204437256, "genuineness": 4.300237655639648, "identity": 0.6995429396629333, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/399873a564d9997731fec6a6b75f787f41001e142cd683b3919e7a24852b4201.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "39c5f552c37c779dbc90711edfce627cf0d46545eaac9f57db458176a4ac45c1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c4e9ca6e5d7951b69de10f154ef5dcfdb8689ea65f1d6a170a566b26f7fed2ff", "generation_seconds_batch": 25.32129802601412, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5567008256912231, "target_z": 0.2675781199957707, "ce": 6.340320587158203, "genuineness": 4.356721878051758, "identity": 0.3699018359184265, "hypothesis": "The 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_Relief/39c5f552c37c779dbc90711edfce627cf0d46545eaac9f57db458176a4ac45c1.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "39dde71c19c842e6cbed7f95dda54a65a230fc60acb8880bbbd83e091c850da8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "bdbc70df42f836ee987606b70e054b8ccd3986712c7885476225ac036dca181e", "generation_seconds_batch": 21.13344213308301, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21183928847312927, "target_z": -0.2265625066723057, "ce": 6.23706579208374, "genuineness": 4.68307638168335, "identity": 0.22050584852695465, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/39dde71c19c842e6cbed7f95dda54a65a230fc60acb8880bbbd83e091c850da8.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "3a3f4fee9b93ce434151b38093d969420044fea096f5e895ad2776e02944bcde", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1bf54e30d295d3eba90678bbf0bc89d0dfb6e7e7a7d087b822c55ddf6f9f701a", "generation_seconds_batch": 27.260622228030115, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0078833103179932, "target_z": 0.9140624959966166, "ce": 6.1020402908325195, "genuineness": 4.406930446624756, "identity": 0.7844822406768799, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3a3f4fee9b93ce434151b38093d969420044fea096f5e895ad2776e02944bcde.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "3ac8d8ad0f04dcb459dccd0f88c8240c76aaad9363f8a8c4bc8fde82984f5dd4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "065ffe38add7b7d94dd0e5365c1eea0f213c1de01ed0414011a1f1d928956441", "generation_seconds_batch": 24.623479183996096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6294519901275635, "target_z": 1.804687584071052, "ce": 6.229123115539551, "genuineness": 4.632867813110352, "identity": 0.6929022669792175, "hypothesis": "J'ai trouvé la 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_Relief/3ac8d8ad0f04dcb459dccd0f88c8240c76aaad9363f8a8c4bc8fde82984f5dd4.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "3adc088a1d73eaa09cdfc554586d0865906aa14ab87563ecea6a155221bc00af", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a661917bfdf54d5c8198803bc4fe8120ef8a8eba04e0a865319bd75a6f58c78e", "generation_seconds_batch": 23.734034743043594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3174786865711212, "target_z": -0.07519532667864963, "ce": 6.292664527893066, "genuineness": 4.607763767242432, "identity": 0.48908063769340515, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3adc088a1d73eaa09cdfc554586d0865906aa14ab87563ecea6a155221bc00af.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "3b0cdf4ae3c9991bfffb917e18012d574ae8e5c77d1ed762112ee5a7f4835cdd", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a17fbb72b6139bbd4c6467a8e6a1e0f3116ce32c6023d420a502f029325af683", "generation_seconds_batch": 24.49929645296652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28987613320350647, "target_z": -0.11474610734482288, "ce": 6.197352409362793, "genuineness": 4.6705241203308105, "identity": 0.481752872467041, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3b0cdf4ae3c9991bfffb917e18012d574ae8e5c77d1ed762112ee5a7f4835cdd.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": "3b499848fc39897f597f808432d7c7309aac176b4148dd0b7c73b76b9df375de", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "aa4fb4bdb9022e923db133394963b41c77a9d0c68376def0cfb792d761020a47", "generation_seconds_batch": 25.247655697050504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5021772384643555, "target_z": 0.18945308529978103, "ce": 6.173524379730225, "genuineness": 4.482243061065674, "identity": 0.8100282549858093, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3b499848fc39897f597f808432d7c7309aac176b4148dd0b7c73b76b9df375de.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "3bb6284d29038103da12a0ba82c7079a5a44c4d5bf9b698c5d9ce4f6f802aa53", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f9c537c98644e6cb668c9758bfd95ff76227dc30b1653cecb060ef98706387d7", "generation_seconds_batch": 24.497134496923536, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4422013461589813, "target_z": 0.10351562399915415, "ce": 5.7684478759765625, "genuineness": 3.785602569580078, "identity": 0.6663811206817627, "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_Relief/3bb6284d29038103da12a0ba82c7079a5a44c4d5bf9b698c5d9ce4f6f802aa53.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "3bbac5aa470424c33e9acb43c079db9080fa5cdcc84137257fbeca65769bd620", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "360b563b864fcd90e2325d31f424fe5c80a0647b62335c8ee81f095f5ffc5dc3", "generation_seconds_batch": 23.742844113963656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9293315410614014, "target_z": 2.234375018682456, "ce": 6.09409761428833, "genuineness": 4.293961524963379, "identity": 0.6917898654937744, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre.", "wer": 0.3684210526315789, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3bbac5aa470424c33e9acb43c079db9080fa5cdcc84137257fbeca65769bd620.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "3c14296c2dda31cd5e07898cd79a941efdfc00e6b5d0b79893dbb69ddaf43bf0", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "31c37cf8e314ac243d430b1e311176b2f610e04b7e8d59b90d937507d2d9e5f7", "generation_seconds_batch": 24.138400629046373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2377379834651947, "target_z": -0.18945312800253758, "ce": 6.09409761428833, "genuineness": 4.432034492492676, "identity": 0.5610893964767456, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3c14296c2dda31cd5e07898cd79a941efdfc00e6b5d0b79893dbb69ddaf43bf0.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "3dc49ab97082e99e3d09a26627eab4edf114f2be767b7c478353afd1b5d7bd83", "generation_seconds_batch": 16.68790042900946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13005395233631134, "target_z": -0.34374999466215544, "ce": 6.205295085906982, "genuineness": 4.413206577301025, "identity": 0.6268330812454224, "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_Relief/3c590f9302048ad206a88d3c2440f1028cc9eea1f1662250baf365be21a6ebfa.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "3d893d190e12150f3939b20f97c7d1e08f4d1af258d79cbd690a132065123ffa", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c9486b760694961a37399ffdb1278d6bc00a704c1d184e2485eda7f902e90574", "generation_seconds_batch": 24.40528574900236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.74344402551651, "target_z": 0.5351562399915414, "ce": 6.372091293334961, "genuineness": 4.080576419830322, "identity": 0.6006944179534912, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3d893d190e12150f3939b20f97c7d1e08f4d1af258d79cbd690a132065123ffa.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "3db24998f8bfadc11f5847dc2cf8d4810ccf60a0be14e37c394a91083091df1e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "412f4a648cab16092c4c8fe1954569c50c7fcb609aacc7badae2eade3c510932", "generation_seconds_batch": 16.920473699923605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3607567846775055, "target_z": -0.013183579321138906, "ce": 6.109982967376709, "genuineness": 4.369274139404297, "identity": 0.2648422122001648, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3db24998f8bfadc11f5847dc2cf8d4810ccf60a0be14e37c394a91083091df1e.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "3dce36926035da6a4a479639b74ca872adfad938b42aa6f7beb6c49ef5db00f1", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f5ccad24a86558aae2407d5cfa82426de28794ab541fb31fd2084f77198059a0", "generation_seconds_batch": 18.756951218936592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6453015804290771, "target_z": 0.39453119461986264, "ce": 6.0305562019348145, "genuineness": 4.394378662109375, "identity": 0.48148372769355774, "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_Relief/3dce36926035da6a4a479639b74ca872adfad938b42aa6f7beb6c49ef5db00f1.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "3e1b0c761d32d203da5d5bbd12fc022ca427c6490a5de0dbadb57465582a9024", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7e42ff3315bfd175662239909df2fb82c8eab59bde60be903436baa5391816a9", "generation_seconds_batch": 23.676856391015463, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6616586446762085, "target_z": 0.4179686879475569, "ce": 6.229123115539551, "genuineness": 4.143336772918701, "identity": 0.5146459341049194, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3e1b0c761d32d203da5d5bbd12fc022ca427c6490a5de0dbadb57465582a9024.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "3e65793bf4cc32c5618931a1604155f825ffc86ca87394ed1d79bf03d63f5239", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "811e36a74ab30f2d9c85a17cff78115593d07e6f0b7dfad63144fb9a0b462400", "generation_seconds_batch": 21.630254888907075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2166101038455963, "target_z": -0.21972656400126878, "ce": 6.078212261199951, "genuineness": 4.3881025314331055, "identity": 0.6194441914558411, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3e65793bf4cc32c5618931a1604155f825ffc86ca87394ed1d79bf03d63f5239.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": "3f38ba5ce1095a6cfecddcdc0ca3f883a7f70c358fac7e35f05806d431406f04", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "17623c0fe56d8de1689982ee1ba7970f5184fcac22b708b9f945fee68468bc1b", "generation_seconds_batch": 17.606630170019343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.37864351272583, "target_z": 1.4453124586317045, "ce": 6.41180419921875, "genuineness": 4.595211505889893, "identity": 0.5536062717437744, "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_Relief/3f38ba5ce1095a6cfecddcdc0ca3f883a7f70c358fac7e35f05806d431406f04.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "3f5e06061f1996badcd3a064676e8054fb8464ea7b74fb052d6ea09960309f97", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1f683ed5503bfeb0b82be5d550d07a6538d9660be311bfe936e0c51315ec9a9d", "generation_seconds_batch": 25.653481898945756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7270869612693787, "target_z": 0.5117187466638471, "ce": 6.2767791748046875, "genuineness": 4.7332844734191895, "identity": 0.8430529832839966, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/3f5e06061f1996badcd3a064676e8054fb8464ea7b74fb052d6ea09960309f97.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "4038aa9e81f94527d6c51595a7e1baa4dd6575c68261e7f899d130534898f747", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "48269130ca89e44697941a8e4fdc67adb24ce76d29aa5c609b1a52f71c04ae71", "generation_seconds_batch": 32.30301510996651, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.315434068441391, "target_z": -0.07812499199323315, "ce": 6.268836498260498, "genuineness": 4.105680465698242, "identity": 0.3942643404006958, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4038aa9e81f94527d6c51595a7e1baa4dd6575c68261e7f899d130534898f747.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": "406826a48c08cbe43cd04c2d89d0170777942312d1314866984f4d2f60dd3944", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c16b1689783d3589ce8015c9e2b64a4d2b87a1c8960c78d45e087acb00195d60", "generation_seconds_batch": 27.88847070094198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5355729460716248, "target_z": 0.2373046839970395, "ce": 6.4912309646606445, "genuineness": 4.469690799713135, "identity": 0.35818737745285034, "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_Relief/406826a48c08cbe43cd04c2d89d0170777942312d1314866984f4d2f60dd3944.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "408bb90928c6a098d40e0b77440a1ca4d0456566d462365e2f502b3faacee437", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d00a4273c474878beffe5cfcdfee556c1d36125b6096761b80c926651f433ddc", "generation_seconds_batch": 25.052806542022154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24523496627807617, "target_z": -0.17871095067780376, "ce": 6.062326908111572, "genuineness": 4.193545341491699, "identity": 0.61362624168396, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/408bb90928c6a098d40e0b77440a1ca4d0456566d462365e2f502b3faacee437.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "40c9785fe30d5f5484a6fbb26f3578ebbc0bbd4025bee0c49a9ab27186d51dca", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "11755652316145d4b4d7dda8a5169efcafc5e9c85cdd94d83ed19b5c45a4291c", "generation_seconds_batch": 22.158343469025567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.583962619304657, "target_z": 0.30664063734376557, "ce": 6.403861999511719, "genuineness": 3.998987913131714, "identity": 0.4687272012233734, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/40c9785fe30d5f5484a6fbb26f3578ebbc0bbd4025bee0c49a9ab27186d51dca.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "4114656b2d4eda9a9adab9f65d563508c06c869a99cd93087bfebed1a2104938", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "db954aad4353784e4f6f81017a72ed0a9f2f00e68929418d561ba914d765ac9b", "generation_seconds_batch": 20.910176348988898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2859535217285156, "target_z": 1.3125000533784457, "ce": 6.24500846862793, "genuineness": 4.086852550506592, "identity": 0.27621904015541077, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4114656b2d4eda9a9adab9f65d563508c06c869a99cd93087bfebed1a2104938.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "414dbb9e56a8f8c2e1b05f710c43a7d728e9e7ffb3b6f8a1c85a256aca375ce2", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a84ddf0ae5a3ac8a465d50314f14b9363aa4e8fd4390d28d3fa87949a85b7bca", "generation_seconds_batch": 22.98299505491741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6384861469268799, "target_z": 0.38476558663424215, "ce": 6.141753673553467, "genuineness": 3.8044304847717285, "identity": 0.3329879343509674, "hypothesis": "The 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_Relief/414dbb9e56a8f8c2e1b05f710c43a7d728e9e7ffb3b6f8a1c85a256aca375ce2.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "414e56fdf71160cc2f7ef248c77a6623eca1d95f8929286db6e8123e063b2dc0", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "8c0cf68a0d2d2eb4f6faf6fc900e55e38af7b203856114e9b3327c071c0eef5a", "generation_seconds_batch": 25.051892729010433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8225032091140747, "target_z": 0.6484375146790725, "ce": 5.935244083404541, "genuineness": 4.2751336097717285, "identity": 0.6244902610778809, "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_Relief/414e56fdf71160cc2f7ef248c77a6623eca1d95f8929286db6e8123e063b2dc0.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "41f4ca70c1a22a75ea441703439a593e5f66485a5b321e8e1efc786ad374de66", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "2d6c38c0c62abe4df646786126fb8b8c1b39fa501d3659d081590be11fba3ac6", "generation_seconds_batch": 24.716100166086107, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8906576633453369, "target_z": 0.7460937653463031, "ce": 6.054384231567383, "genuineness": 4.406930446624756, "identity": 0.750232458114624, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/41f4ca70c1a22a75ea441703439a593e5f66485a5b321e8e1efc786ad374de66.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "425830ddc24c3f7568714a6a0e473de449a679f2b2ce86883b3a4650d254103a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "61bd6da05f2e51f3788c6a27db860d40f11d8a75b16165dbce9665055d244caf", "generation_seconds_batch": 21.590063824900426, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23024100065231323, "target_z": -0.20019530532727137, "ce": 6.221180438995361, "genuineness": 4.507347106933594, "identity": 0.6216788291931152, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/425830ddc24c3f7568714a6a0e473de449a679f2b2ce86883b3a4650d254103a.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": "42a7da819c7df1cafb2886a8dd3b27e839ff62ce88aa51b20bf3fba46b59bf02", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c167a3f6cf14f7006fc3b800b9c5989d1f99d8168c868313328d5cd10716f28a", "generation_seconds_batch": 17.417378176003695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.740717887878418, "target_z": 0.531250048040601, "ce": 6.41180419921875, "genuineness": 4.369274139404297, "identity": 0.5272236466407776, "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_Relief/42a7da819c7df1cafb2886a8dd3b27e839ff62ce88aa51b20bf3fba46b59bf02.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "42c90e288cdf106e9b758ba99550e28c794a7a37d324621b5ac066de1715a5cb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "2000848fc5c3f2610acea18d46df3ae07e24d7541f2535ba0616378c9e3a1d02", "generation_seconds_batch": 21.483410452958196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23433026671409607, "target_z": -0.1943359319953478, "ce": 6.141753673553467, "genuineness": 4.432034492492676, "identity": 0.6485199928283691, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/42c90e288cdf106e9b758ba99550e28c794a7a37d324621b5ac066de1715a5cb.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "42e5f2c579e5838382fa7fc9f5d110229ba5eda2e49a63dc20b18f67901d7a36", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f61b7dfc79ef3e4333b84cbb822a27cadccfd22c60a283a4a85ab5bbc77ec6ad", "generation_seconds_batch": 25.67964490898885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36859452724456787, "target_z": -0.0019531386782267015, "ce": 5.974957466125488, "genuineness": 3.9173994064331055, "identity": 0.2976512014865875, "hypothesis": "The 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_Relief/42e5f2c579e5838382fa7fc9f5d110229ba5eda2e49a63dc20b18f67901d7a36.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": "4313b6fffad85c2aeb4b4594a964e721c2cf297e35ee07512ed0758241544077", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "61cb0a5ab4bda3197d578da7c60cbed8af60b0a423f736418acd799999278592", "generation_seconds_batch": 22.887618473963812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6671110391616821, "target_z": 0.42578124266046374, "ce": 6.046441555023193, "genuineness": 4.331617832183838, "identity": 0.48665371537208557, "hypothesis": "J'ai créé le numéro sur l'enveloppe. Lise le bien and verify the two dernier chiffres. Appelle moi quand tu rentres.", "wer": 0.45454545454545453, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4313b6fffad85c2aeb4b4594a964e721c2cf297e35ee07512ed0758241544077.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "deaa7daaf896cc8cc68e64e1778edca5a8e7ccbddd4061fc63e6a9b4555085c9", "generation_seconds_batch": 19.387738354038447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16822044551372528, "target_z": -0.2890624959966166, "ce": 6.141753673553467, "genuineness": 4.482243061065674, "identity": 0.7512425184249878, "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_Relief/434f953004ee3838b31e4f505ba0cb9202b34ab37936979fff50edb64a6a996f.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "436c279c42c381b68d9a191026195c072bf4d69a953865c235915f0cb825cf18", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "b6518179acbf2814d2d82b254cd47f5b4632ac44352f8ee4cc86edf918ebb35c", "generation_seconds_batch": 22.415161711047404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7461702227592468, "target_z": 0.5390625173479948, "ce": 6.006728172302246, "genuineness": 4.18726921081543, "identity": 0.1837756335735321, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/436c279c42c381b68d9a191026195c072bf4d69a953865c235915f0cb825cf18.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "43b66d774009fdeb1553ff856211ff090eaaafd66f439485c9b4269d35dbcea5", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "893635a5d376e1f97bac23329eec6550bc265ae2be3e4a07775d7870439c9437", "generation_seconds_batch": 23.60475362103898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2259775400161743, "target_z": 1.2265624639695492, "ce": 6.252951145172119, "genuineness": 4.419482707977295, "identity": 0.5555887222290039, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/43b66d774009fdeb1553ff856211ff090eaaafd66f439485c9b4269d35dbcea5.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "43cf09e4bfae1c6988999ab06fdfb0218d20175ae23c1d35dc6cbb4957547cc9", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "af594c1631bad6347934ede2070d2965f77c3ff5d0d2c0d4778179309135fa42", "generation_seconds_batch": 23.709191934904084, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0951210260391235, "target_z": 1.0390625173479948, "ce": 6.038498878479004, "genuineness": 4.319066047668457, "identity": 0.6444413065910339, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/43cf09e4bfae1c6988999ab06fdfb0218d20175ae23c1d35dc6cbb4957547cc9.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "355614c18cd2d99b9d93bb6af06b4c0bbc0dea615b58f22e4d65bd64ab7feb08", "generation_seconds_batch": 16.89829314209055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5171712636947632, "target_z": 0.21093752535476168, "ce": 6.284721851348877, "genuineness": 4.65797233581543, "identity": 0.6282851099967957, "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_Relief/43d771a5c055e2aea1186dc99f4cdef2b4c6bc8c6b2779ad35a29ca11c75a91c.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "43df4b04d91b50d97c9983dd1c31bca6c6ffea75daaa0ccefbadf4764f7456f0", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7294e5b805f01989c0046f855391345e372f623489848a418c2438ada79008f9", "generation_seconds_batch": 18.585352052934468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40727218985557556, "target_z": 0.0534667976673363, "ce": 6.197352409362793, "genuineness": 4.482243061065674, "identity": 0.7496573328971863, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/43df4b04d91b50d97c9983dd1c31bca6c6ffea75daaa0ccefbadf4764f7456f0.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "441fccb698b0f47938aa1699b2d3ca673434c1a0cdbbe1d55a48db809a04f5c2", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e6e5c942fc39e00b0215edec2ad4a7f9c92b9547f1873c23cb8e678256929c64", "generation_seconds_batch": 23.973733845050447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1368694007396698, "target_z": -0.33398436532515674, "ce": 6.046441555023193, "genuineness": 4.174716949462891, "identity": 0.6480183601379395, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/441fccb698b0f47938aa1699b2d3ca673434c1a0cdbbe1d55a48db809a04f5c2.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "446c5d0bf6c1b1c905553528b7c62389a24ad9990faa068caa1a060b890c1f2b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "25034a79379281c8caaacd821ac743fc59b040a8f03bf0c2552217c29229db49", "generation_seconds_batch": 22.545159319997765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8497649431228638, "target_z": 0.6874999466215543, "ce": 6.252951145172119, "genuineness": 4.7332844734191895, "identity": 0.5120372176170349, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro de la casa?", "wer": 0.17647058823529413, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/446c5d0bf6c1b1c905553528b7c62389a24ad9990faa068caa1a060b890c1f2b.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "4503f1900afc648e92f8aa78285640ecec5dc133618e06dbea7603fec3d8611c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "2fd6f9de94daf9c22683c6306025d581615b0860f674ecc22c086b902540fa36", "generation_seconds_batch": 18.09948416100815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6458089351654053, "target_z": 1.82812490658772, "ce": 6.141753673553467, "genuineness": 4.325342178344727, "identity": 0.4387284815311432, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4503f1900afc648e92f8aa78285640ecec5dc133618e06dbea7603fec3d8611c.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": "456f2a9034689f7f596ead6fee23da137ebcdad41cabbdd19f0b3b82c2747af3", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1b7f5905c136c04f10302742ed053a622452c2599d676decfaa824116835be51", "generation_seconds_batch": 26.119101432967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2641440629959106, "target_z": 1.2812500053378446, "ce": 6.260893821716309, "genuineness": 4.494794845581055, "identity": 0.6571530699729919, "hypothesis": "Ton message is arrived after my départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.19047619047619047, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/456f2a9034689f7f596ead6fee23da137ebcdad41cabbdd19f0b3b82c2747af3.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "28ee91de5e1d7eb76a684c979af8fd2b47749615ab09714690fce4461836db64", "generation_seconds_batch": 16.791992221958935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27726757526397705, "target_z": -0.13281249065877201, "ce": 6.316492557525635, "genuineness": 4.331617832183838, "identity": 0.6701661348342896, "hypothesis": "Ich schrieb die Nummer auf den Umschlag, ließ sie genau und prüfe die letzten beiden Ziffern. Ruf an, wenn du Zeit hast.", "wer": 0.045454545454545456, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/45f9ec8497c8691f9e18d794cf98f47c522bfab041b36df5accabf5c5c456412.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": "460c418f5ad56eb5305668649ef45b2331df4f8f343df74b595ad2866cb3c66f", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "afc578279b57a758ed7d260e641bf9a07527a66638e4a0d556c14533f19607f6", "generation_seconds_batch": 17.537423270987347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0787639617919922, "target_z": 1.0156250240203006, "ce": 6.252951145172119, "genuineness": 4.319066047668457, "identity": 0.629645586013794, "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_Relief/460c418f5ad56eb5305668649ef45b2331df4f8f343df74b595ad2866cb3c66f.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": "46a155e34971687da4e3b49dcd416fd26f6249d25018f48f0eaf84704ae26a36", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ca2152c5b6c046c55329be5c0a94aa468c0551aa76b4717de9542c42d07c1c02", "generation_seconds_batch": 19.490673589985818, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4036940932273865, "target_z": 0.04833986201543688, "ce": 6.038498878479004, "genuineness": 4.457139015197754, "identity": 0.7442147135734558, "hypothesis": "Quelqu'un a deplacé le petit chaise bleu. Elle était ici, près de la grand bibliothèque.", "wer": 0.5238095238095238, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/46a155e34971687da4e3b49dcd416fd26f6249d25018f48f0eaf84704ae26a36.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "4706443bb9628b1eb81127ddf8d3d11fbce096298beabe326bf42453b695d6cb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "33c9cbcc4918aa1b765b9506b2ff8247d42c7b6165c9aed03f8ef24debd788c1", "generation_seconds_batch": 16.410002109012567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4168100357055664, "target_z": 1.5, "ce": 6.141753673553467, "genuineness": 4.532451152801514, "identity": 0.6963070631027222, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4706443bb9628b1eb81127ddf8d3d11fbce096298beabe326bf42453b695d6cb.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": "4736135a296450330f888b28b13d92eed6c0562d0880286eda2152ca9697781e", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "501fc32f14641ecc5c72d0968e1db006e13705801d201f79f244b566a02f03fe", "generation_seconds_batch": 25.522787277936004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5055849552154541, "target_z": 0.19433588929259127, "ce": 6.284721851348877, "genuineness": 3.7667744159698486, "identity": 0.12362635135650635, "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_Relief/4736135a296450330f888b28b13d92eed6c0562d0880286eda2152ca9697781e.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "4c402497854dfb291726dfdfd9afb2a0483b08dcaeca6b7781b72a1625bff9cd", "generation_seconds_batch": 22.91816745197866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25545814633369446, "target_z": -0.16406249599661657, "ce": 6.078212261199951, "genuineness": 4.532451152801514, "identity": 0.800294041633606, "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_Relief/47d00b404f769e82194cfb39f2be7a6bd3cc5bfaac4f38356b0fada2abdb9f4d.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": "47e0500963858d4c06643c66b9660262376ed5628486e4cc0e9a47d6f4f285ee", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1007c75ce6b119bff982b5e5f6c7189a969240fa98fe90ef65b1649f2a6ef418", "generation_seconds_batch": 17.637080927030183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8361340761184692, "target_z": 0.6679687306503135, "ce": 6.459460258483887, "genuineness": 4.369274139404297, "identity": 0.42473727464675903, "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_Relief/47e0500963858d4c06643c66b9660262376ed5628486e4cc0e9a47d6f4f285ee.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": "47ece9e8280e5ecb8763ad31885a1a25185bef79ad350a93d1d7b10a59c75074", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fa9b6f84480995090109f9ffbd041e4b071ceabc418c29a2b8db393a140aa7f8", "generation_seconds_batch": 18.62828514992725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3677388429641724, "target_z": 1.4296875200169172, "ce": 6.213237762451172, "genuineness": 4.406930446624756, "identity": 0.6582343578338623, "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_Relief/47ece9e8280e5ecb8763ad31885a1a25185bef79ad350a93d1d7b10a59c75074.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "480d18996b9251a157f61a67a59ff21e671beba96ece60411750eefacefdcf35", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ecabf7de061890e34819fa777d936b623a8a06bb3790f962a344c85d36cc230f", "generation_seconds_batch": 25.196564748999663, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09325054287910461, "target_z": -0.39648437600084585, "ce": 6.117925643920898, "genuineness": 4.20609712600708, "identity": 0.6003659963607788, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/480d18996b9251a157f61a67a59ff21e671beba96ece60411750eefacefdcf35.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": "48d17c83baa4abb84078dfa92a98ec55b9618d8211d4303a05a8f7b168c5c0c7", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo podemos hablar.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Natural clear speech.) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo podemos hablar.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8512fb7c7322cc6c2ad8920dfc5cfc809bb1fad60c3e4722109076705a4c2f94", "generation_seconds_batch": 16.965002275072038, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.324120044708252, "target_z": 1.3671875947467411, "ce": 6.252951145172119, "genuineness": 4.394378662109375, "identity": 0.5823813080787659, "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_Relief/48d17c83baa4abb84078dfa92a98ec55b9618d8211d4303a05a8f7b168c5c0c7.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": "48f2ca56a447eb9085675032f4ac00dae125bd8723cf00a0862c63cc404db551", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2abb74900a4ddd46a472aeb78662bf4677aa6b0645b54b3702fe34086cc0c191", "generation_seconds_batch": 17.74637057702057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4939987361431122, "target_z": 0.17773438133869043, "ce": 6.4912309646606445, "genuineness": 4.231201171875, "identity": 0.544463038444519, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade, dann neben dem Fenster. Nimm sie mit, wenn du gußst.", "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_Relief/48f2ca56a447eb9085675032f4ac00dae125bd8723cf00a0862c63cc404db551.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "4974819ed350fb4e06f5051e90ff9b8108f0c8746316ae1189da2a4eaa0209e0", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9f376a1f514335e95b30d64096935cea73a0d14c7e52026bc3a92c2f7b580867", "generation_seconds_batch": 25.157097224029712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7298130989074707, "target_z": 0.5156249386147875, "ce": 6.395919322967529, "genuineness": 4.419482707977295, "identity": 0.46918272972106934, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4974819ed350fb4e06f5051e90ff9b8108f0c8746316ae1189da2a4eaa0209e0.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "4985a94b9706023fe0874262e020595a0f3e1f6df340a5ce18e5470643bf2fcf", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "3cacbd5914992749b1d75608cd424a93ff00860148963e39cc70e75e54cb4d9d", "generation_seconds_batch": 23.84896593890153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.37864351272583, "target_z": 1.4453124586317045, "ce": 6.133810997009277, "genuineness": 4.319066047668457, "identity": 0.7488033771514893, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4985a94b9706023fe0874262e020595a0f3e1f6df340a5ce18e5470643bf2fcf.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "49860cef5441ea065d96fd86857cbf1f9eddf37f422f3e538838e825d2e19f6a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5d876c6bcfb10628f597ea021805631033e55f20d881fcbcfde2ec7d45ce7ffb", "generation_seconds_batch": 28.890790439909324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.160549283027649, "target_z": 1.132812490658772, "ce": 6.213237762451172, "genuineness": 4.419482707977295, "identity": 0.2816706895828247, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/49860cef5441ea065d96fd86857cbf1f9eddf37f422f3e538838e825d2e19f6a.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "49af8cd9d600085da65af338c160b4aaa0add8c164d3592fcee1c4c76fdf8e7e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8951490fcb563461ad7181e52c63e351d8adc80dcbdb6b27e66838b2dc72a56c", "generation_seconds_batch": 23.383719385019504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6998251676559448, "target_z": 0.4726562293158523, "ce": 6.133810997009277, "genuineness": 3.6914620399475098, "identity": 0.48283863067626953, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/49af8cd9d600085da65af338c160b4aaa0add8c164d3592fcee1c4c76fdf8e7e.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "0b95a0d09ce391c249edf0f2b70db1112e938ae8b10940adc3bb5cbb25ed7f2c", "generation_seconds_batch": 20.788874376914464, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0024309158325195, "target_z": 0.9062499412837097, "ce": 6.117925643920898, "genuineness": 4.18099308013916, "identity": 0.573993980884552, "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_Relief/49d468ae6540cc7c1e5b0e6883c25e2b29599458c9de0a5398000eaca62677ab.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": "4a02f15034034afc289b789054412cd8b411902eb5e3dc08b322c6358827d29f", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2212598134f2ad4bbe87a1f0de9a50c1565a4d0eccd401624fbcabeef32ac72d", "generation_seconds_batch": 16.223765004076995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4939987361431122, "target_z": 0.17773438133869043, "ce": 6.3641486167907715, "genuineness": 4.068024158477783, "identity": 0.23712360858917236, "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_Relief/4a02f15034034afc289b789054412cd8b411902eb5e3dc08b322c6358827d29f.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "4a13b56e9686d88a1671511bbb953666c408116dfeb336d1f6aacf9da10d50d2", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e8116e97da0264575dcb13fda89a8eea3cdd427340685fc0fb2b71e79bfc27a1", "generation_seconds_batch": 23.1959709119983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4713335037231445, "target_z": 1.5781248638849636, "ce": 5.95112943649292, "genuineness": 4.287685871124268, "identity": 0.7597119808197021, "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_Relief/4a13b56e9686d88a1671511bbb953666c408116dfeb336d1f6aacf9da10d50d2.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "4a24d3a1179b3690572c4e08f44e58fa7e63beb2300f8afce025431e627a4dc4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ffd85b899e39e05e86ab48f50cfcaff2f23756bdbbc8c97470f1ede9bf42d74f", "generation_seconds_batch": 16.11930110596586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1114780902862549, "target_z": 1.0625000106756892, "ce": 6.221180438995361, "genuineness": 4.482243061065674, "identity": 0.539229691028595, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4a24d3a1179b3690572c4e08f44e58fa7e63beb2300f8afce025431e627a4dc4.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "4b20abd9db60d489173440edd101a619e993f80144248f98c3fcbee3a2ade09c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d28a19075ea6b01ec75fb1a61a87674144db6bfa052675b927510d20c4b7b041", "generation_seconds_batch": 25.6667007219512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7625272870063782, "target_z": 0.5625000106756891, "ce": 6.24500846862793, "genuineness": 3.9299514293670654, "identity": 0.3212738037109375, "hypothesis": "The 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_Relief/4b20abd9db60d489173440edd101a619e993f80144248f98c3fcbee3a2ade09c.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "4b8d0f8730c0ce143b58d122cb005a584843f6d780dc204cda045b0e1602f542", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e7f4bacbd21b6a1e187358546e8687c95a96e42637218bff09e8cf38e4b4b002", "generation_seconds_batch": 17.1578430730151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8497649431228638, "target_z": 0.6874999466215543, "ce": 6.292664527893066, "genuineness": 3.860914945602417, "identity": 0.3116344213485718, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4b8d0f8730c0ce143b58d122cb005a584843f6d780dc204cda045b0e1602f542.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "4c6a165720e0ddd28b6244f1d8161be5fb11f1b11d2e3e76adfadae5f2fc2c9c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "6ebdaa2123d8d1d1b01b1d1e23da9200daf2b051f32017dd60ea1ae18da446bc", "generation_seconds_batch": 21.174144941032864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8879314661026001, "target_z": 0.7421874879898497, "ce": 6.141753673553467, "genuineness": 4.607763767242432, "identity": 0.6164958477020264, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4c6a165720e0ddd28b6244f1d8161be5fb11f1b11d2e3e76adfadae5f2fc2c9c.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "4c7913c415185f4ead7a9c760faaee77f3608368ed0dd35958e9fedc84d53803", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "8672950c663ca6d906fa9ca904051353d2fd0300589e72f56e820599a603de6a", "generation_seconds_batch": 21.988933731918223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6221290826797485, "target_z": 0.36132809330654786, "ce": 6.284721851348877, "genuineness": 3.9048471450805664, "identity": 0.2728356719017029, "hypothesis": "The 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_Relief/4c7913c415185f4ead7a9c760faaee77f3608368ed0dd35958e9fedc84d53803.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "4d2dc24d77d3277f376b1a34e41d601f2eac9b30b2760d781a7116b3171e6238", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "bd9484d458bb0d8d806570964c310f06839cc9c678da7301782589547b695c66", "generation_seconds_batch": 25.6667007219512, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6752895712852478, "target_z": 0.4374999893243109, "ce": 6.181467056274414, "genuineness": 4.256305694580078, "identity": 0.41626912355422974, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4d2dc24d77d3277f376b1a34e41d601f2eac9b30b2760d781a7116b3171e6238.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "4d70a84eb5bf5301efe901e22031169f621993d2472fd36d936842fabfd31432", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "ffb3072561439745f5d3f45fedb1c4f70f9889e0e78cd32f8bfbc032410b1653", "generation_seconds_batch": 20.010627805953845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14504793286323547, "target_z": -0.3222656186613096, "ce": 6.141753673553467, "genuineness": 4.13078498840332, "identity": 0.3990921378135681, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4d70a84eb5bf5301efe901e22031169f621993d2472fd36d936842fabfd31432.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "4d8595150e63151ace987a451799e4ecde76c53c0e1a01af8da5fd6f528a3c85", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "74c9197f3ff24ed045ba3adf4e2951f4d1436ef6bc6ae9e9f310262b18e9fb27", "generation_seconds_batch": 24.943288597045466, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.860669732093811, "target_z": 0.703125056047368, "ce": 6.292664527893066, "genuineness": 3.9676074981689453, "identity": 0.40106236934661865, "hypothesis": "The 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_Relief/4d8595150e63151ace987a451799e4ecde76c53c0e1a01af8da5fd6f528a3c85.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "4d96143c9e7785e29c6d026a3acc6d6b288fbb683c41fdf4657561bc1037b990", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "60eae64a652f919f58c095676dd975520ae3b07c85f17d71648557dec902077d", "generation_seconds_batch": 26.4223464820534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3895483016967773, "target_z": 1.4609375680575183, "ce": 6.340320587158203, "genuineness": 4.469690799713135, "identity": 0.8234342932701111, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4d96143c9e7785e29c6d026a3acc6d6b288fbb683c41fdf4657561bc1037b990.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "4dfa5ed897c098c6f45014ac67f3f28a2837a0242ea48974887006673772e05a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bc165ca4517b0298e3da37645392ae8116e42b7f7a72b5751338bac82dd68b76", "generation_seconds_batch": 16.598384245997295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3263387680053711, "target_z": -0.06250001067568914, "ce": 6.054384231567383, "genuineness": 4.381826400756836, "identity": 0.38737165927886963, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4dfa5ed897c098c6f45014ac67f3f28a2837a0242ea48974887006673772e05a.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "4e3053415ec63523739fbfd246511c33983dcdaf3ce5c1e27c33799c76d9c47d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1dfd1dfc853ce66d41dabf50be32fd9b74b6e000b6f49b2fea8c7d9639f7fbbe", "generation_seconds_batch": 17.668190366006456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0274739265441895, "target_z": 2.3749999786486216, "ce": 6.229123115539551, "genuineness": 4.281409740447998, "identity": 0.6668673753738403, "hypothesis": "I truth la petite boîte. Elle était près de la vieille fenêtre.", "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_Relief/4e3053415ec63523739fbfd246511c33983dcdaf3ce5c1e27c33799c76d9c47d.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "4ea5b615c9f728a8fe2f2ebabe83434ea579952059e9bd3fe59bce183d3790b3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "b59dd880df0793ef534157639b2c01a9fffb0364109a38a53ca0eb4a74554dbc", "generation_seconds_batch": 17.227407495956868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5858330726623535, "target_z": 1.7421874879898498, "ce": 6.229123115539551, "genuineness": 4.482243061065674, "identity": 0.7689607739448547, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4ea5b615c9f728a8fe2f2ebabe83434ea579952059e9bd3fe59bce183d3790b3.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "4efbc37a56c843b47453c18e9dede6bc96bb22f3de98cf69ea166cfad724e736", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2c91f638bdbd9a48095489f4ed1839cb3d4b6545e408de374536c529cda6ea88", "generation_seconds_batch": 25.20946493104566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17503589391708374, "target_z": -0.27929686665961784, "ce": 6.221180438995361, "genuineness": 4.519899368286133, "identity": 0.6810426115989685, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4efbc37a56c843b47453c18e9dede6bc96bb22f3de98cf69ea166cfad724e736.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "4f07717cbc9b9c62169e56466c599dcb9e95336fa2d7bc4098d85ebc16be924e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "cee4dea1068abfc21fbf17528af5500a65fba7345ca289b0877ae38329f8c8fd", "generation_seconds_batch": 20.649259333964437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3622864484786987, "target_z": 1.4218749653040104, "ce": 6.23706579208374, "genuineness": 4.281409740447998, "identity": 0.5996168851852417, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4f07717cbc9b9c62169e56466c599dcb9e95336fa2d7bc4098d85ebc16be924e.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "4f48c2b16fb354ba59ca137b9a0c26b857251dfdbcd1db96fdfa581c70887b5b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "97c6e271e9027f56fba7dc0b5d3a70c547855027c838b4b2728c3d9d13d118eb", "generation_seconds_batch": 23.230745112989098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8661220073699951, "target_z": 0.7109374399492486, "ce": 5.704906940460205, "genuineness": 3.785602569580078, "identity": 0.4655749201774597, "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_Relief/4f48c2b16fb354ba59ca137b9a0c26b857251dfdbcd1db96fdfa581c70887b5b.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "4f6f9c4212f68bf8f698e400afecb3102b67a393e518a3ffee041f92af8a2a0b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "45699e3ac358dce951118796113713659b4d0713116e43407d0a0b07f07fce09", "generation_seconds_batch": 20.944683080073446, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4440717697143555, "target_z": 1.5390624319424817, "ce": 6.324435234069824, "genuineness": 4.457139015197754, "identity": 0.4712996482849121, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/4f6f9c4212f68bf8f698e400afecb3102b67a393e518a3ffee041f92af8a2a0b.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "503252399a306b7b3ee857dfa2802f60e04843e2f6889264472630aeebf54f37", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "547e81817340ea825fab0130580baf98649de3b993a5aea872b0c01d42d928e6", "generation_seconds_batch": 16.794014494051225, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8497649431228638, "target_z": 0.6874999466215543, "ce": 5.998785495758057, "genuineness": 3.998987913131714, "identity": 0.4262685775756836, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás linda.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/503252399a306b7b3ee857dfa2802f60e04843e2f6889264472630aeebf54f37.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "5057e97d931946507b4e479fb20938e6f5b75498636efd5337df3b021a8de66f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7cc8bc4f7d97afd180fb340a8bccc5e58be978b6d6d5a47ae414776bd8c0d306", "generation_seconds_batch": 18.199155142065138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24046416580677032, "target_z": -0.18554687199746242, "ce": 6.284721851348877, "genuineness": 4.595211505889893, "identity": 0.6694289445877075, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5057e97d931946507b4e479fb20938e6f5b75498636efd5337df3b021a8de66f.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "50de12d1ebe759f8cad9e6e36e250366ad23d3e868851a18c374fbb1be6fa832", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "f982f64ddfef36753703874519888ebd3f41ec46fb1efa1287bc1adda65dae3a", "generation_seconds_batch": 26.865102300071158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2205252647399902, "target_z": 1.2187500800676685, "ce": 6.0146708488464355, "genuineness": 4.099404335021973, "identity": 0.3480992317199707, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/50de12d1ebe759f8cad9e6e36e250366ad23d3e868851a18c374fbb1be6fa832.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "512a2d7e1635ba3d6e0f6849cba922105e26012416b3974a605bcad404ff09d4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c66281b3be5e4dd3e6bdc7edf9349bc59c6cc5367b13228a9371fc0ec0886181", "generation_seconds_batch": 24.339464670047164, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2695963382720947, "target_z": 1.2890623892397253, "ce": 6.022613525390625, "genuineness": 4.20609712600708, "identity": 0.626334547996521, "hypothesis": "Te he encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/512a2d7e1635ba3d6e0f6849cba922105e26012416b3974a605bcad404ff09d4.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": "517228832583dd4248d1cca352a1be43752daf961fe7bfacd1fd873c943e037c", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a26cb695345c3d6fbe75190dd1e47c76abdb7bfd6bce8e4bc9da78a00a4caf0c", "generation_seconds_batch": 17.302961291978136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4384528398513794, "target_z": 0.09814451398540898, "ce": 6.475345611572266, "genuineness": 4.482243061065674, "identity": 0.39441370964050293, "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_Relief/517228832583dd4248d1cca352a1be43752daf961fe7bfacd1fd873c943e037c.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "51800a85b5e03c20df477d5e12619ba4845972fa22e688bbc9f9f88c65f5d944", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "711d6299f04097c92ebea74b8117a675fd528e784c1d31ee758fea4185fe1c17", "generation_seconds_batch": 18.756951218936592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6916466355323792, "target_z": 0.4609374826520052, "ce": 5.792276382446289, "genuineness": 4.042920112609863, "identity": 0.44557633996009827, "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_Relief/51800a85b5e03c20df477d5e12619ba4845972fa22e688bbc9f9f88c65f5d944.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": "51e5a9139c94a19c98292a700e06aad4d66d649f1462f2b8b2b83145f64d5a79", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "951ae6b6baf389a002a77f0a11d860684da2c9085fb78bd381ab596db3c711b3", "generation_seconds_batch": 19.58621364296414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4289112389087677, "target_z": 0.08447267134609167, "ce": 6.197352409362793, "genuineness": 4.507347106933594, "identity": 0.4759597182273865, "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_Relief/51e5a9139c94a19c98292a700e06aad4d66d649f1462f2b8b2b83145f64d5a79.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "51f1747b0a268d041b3110acda6df3ebf5e6dccff97c03ccd53fe2e27e204bb1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d683d0fdec8602b6a819415738014270c2d6b7d327b2d15ffb0c6c6d1fa1e437", "generation_seconds_batch": 20.704614597023465, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36126792430877686, "target_z": -0.012451184343871291, "ce": 6.467403411865234, "genuineness": 4.193545341491699, "identity": 0.592758297920227, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/51f1747b0a268d041b3110acda6df3ebf5e6dccff97c03ccd53fe2e27e204bb1.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "51fad034c9c078cccc319b335161b00fadd0cd264317a64e0f89768c8c36ee70", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "75de84f02cae11d53a152adccdafa09fdd4c97217d18201bbc7a82e2f1c83dad", "generation_seconds_batch": 15.49601408408489, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29839545488357544, "target_z": -0.10253905466004079, "ce": 6.308549880981445, "genuineness": 4.457139015197754, "identity": 0.6556289196014404, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/51fad034c9c078cccc319b335161b00fadd0cd264317a64e0f89768c8c36ee70.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "520ff8566f61cdc5ccdd02ee5fff0c5c1ba5116a1d335317571324c3d3f47221", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c1b2e85ed39f1cb4f0f442185114105544f240ec11882461318cab68dad2ce00", "generation_seconds_batch": 15.99066079291515, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7325392961502075, "target_z": 0.5195312159712409, "ce": 6.149696350097656, "genuineness": 3.7918784618377686, "identity": 0.45141807198524475, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/520ff8566f61cdc5ccdd02ee5fff0c5c1ba5116a1d335317571324c3d3f47221.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "52128184de5475d3dc28787f124387a0cd27415a59eff76020ecb4bd1be9a743", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8c3d36e8dcda99db073898902673aeaee1d4dd2ceb054791b9809935023b77ec", "generation_seconds_batch": 24.771130832028575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1441922187805176, "target_z": 1.1093749973310778, "ce": 6.23706579208374, "genuineness": 4.469690799713135, "identity": 0.6534820795059204, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/52128184de5475d3dc28787f124387a0cd27415a59eff76020ecb4bd1be9a743.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": "52f3506e3edd04d438e8874aa4ac5131c818a1687bf37490a5cdc2794cfe238a", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0b2ef3771916daa8fe87b9cfdf8dd48f3c499d5c7d362ec5c5fa14b21b1b8539", "generation_seconds_batch": 18.855725826928392, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.838860273361206, "target_z": 0.6718750080067668, "ce": 6.078212261199951, "genuineness": 4.595211505889893, "identity": 0.6256746053695679, "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_Relief/52f3506e3edd04d438e8874aa4ac5131c818a1687bf37490a5cdc2794cfe238a.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "52fb987c985bcab33e16b2fab227a43704c9393216d0faf697354fad2533849d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9bee59fcc653449ecc6e9fb3407abbd7576b00894c9070008bb3888a856af58e", "generation_seconds_batch": 29.61819564900361, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5294390320777893, "target_z": 0.22851560264777587, "ce": 6.173524379730225, "genuineness": 4.419482707977295, "identity": 0.7054684162139893, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/52fb987c985bcab33e16b2fab227a43704c9393216d0faf697354fad2533849d.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "532f43bce6f86e8c66713be3c7efbb0784e2b329340d88f0098d9a97168ebf90", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a98d27958640d18abc27acc84cc3582df58f000771c28327a41cc10c12e543bc", "generation_seconds_batch": 27.853794640046544, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2268332690000534, "target_z": -0.20507813067145986, "ce": 6.149696350097656, "genuineness": 4.519899368286133, "identity": 0.6404314041137695, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/532f43bce6f86e8c66713be3c7efbb0784e2b329340d88f0098d9a97168ebf90.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "53a90834fc924ac243df6f121ef169150baf518c242f53423f728842f9b916a8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "59d19ebb4b7875787b6acd726b7365f1a10226718d7bf5c8dd52f39188e58090", "generation_seconds_batch": 15.789189751958475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9124670624732971, "target_z": 0.7773437279813912, "ce": 6.125868320465088, "genuineness": 4.532451152801514, "identity": 0.5368056297302246, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/53a90834fc924ac243df6f121ef169150baf518c242f53423f728842f9b916a8.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "5442dbe147f0ef89d318b666ee4bb70aa2915bb656428e8791a593f92903afa7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8a520549a4e3e8ab2c6262e75388a1fc6ba9009017bc663aaedc11a5d858d0a5", "generation_seconds_batch": 16.622751369024627, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.395000696182251, "target_z": 1.468750122770425, "ce": 6.24500846862793, "genuineness": 4.457139015197754, "identity": 0.32150980830192566, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5442dbe147f0ef89d318b666ee4bb70aa2915bb656428e8791a593f92903afa7.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "aa4f5a26f2d820572fb835a3a200b3c6890b0f4d5e4a5f54d3897db09ac4aa7e", "generation_seconds_batch": 16.791992221958935, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2520504295825958, "target_z": -0.16894529998942678, "ce": 6.300607204437256, "genuineness": 4.7081804275512695, "identity": 0.6722875833511353, "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_Relief/546203f143d2dbd908be3097fd76d41d76e93afd1487fa15c64a3d119dff5d49.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "54769a3704b1d69f42dce981d364b93f6b531159f8c4282a65c84523787ce97e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "219afb7e7cbdcb6dd6ebb502369d38155ab6ddb0eace303740ee5b8f8d507354", "generation_seconds_batch": 28.30075575201772, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21865473687648773, "target_z": -0.216796877335307, "ce": 6.1894097328186035, "genuineness": 4.457139015197754, "identity": 0.6262164115905762, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/54769a3704b1d69f42dce981d364b93f6b531159f8c4282a65c84523787ce97e.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "547c1cf6abb45808a8461b6699a2923e72f8b144be31b78a59c144449b7bf94b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "ccffb41fca01bb9674dd1274a693e0d48062f553fccf9f1198682a25eeb45fa4", "generation_seconds_batch": 20.8753685640404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7788843512535095, "target_z": 0.5859375040033834, "ce": 6.221180438995361, "genuineness": 4.030367851257324, "identity": 0.37013983726501465, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/547c1cf6abb45808a8461b6699a2923e72f8b144be31b78a59c144449b7bf94b.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": "547dac5c5e2f2ba3328afd58b50210502a726afb0fa32c692952f9118cf18f6e", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "f110c12471851a35e15a32e14553c276eeef1cbb3df6f42763fdc8e5521e9943", "generation_seconds_batch": 20.19425267796032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1477741003036499, "target_z": -0.3183593840076127, "ce": 6.054384231567383, "genuineness": 4.432034492492676, "identity": 0.36513009667396545, "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_Relief/547dac5c5e2f2ba3328afd58b50210502a726afb0fa32c692952f9118cf18f6e.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "548b387a05aad262d8ab8c7f0fe83c0adbb68ad2f006ff12041a3bfb1fdf910e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dc947a835099701a7beeb03fd209de2a6115582261b6403a152b9b437e7fb45b", "generation_seconds_batch": 25.323077872977592, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6861943006515503, "target_z": 0.4531250133446114, "ce": 5.839932441711426, "genuineness": 4.21237325668335, "identity": 0.3715394139289856, "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_Relief/548b387a05aad262d8ab8c7f0fe83c0adbb68ad2f006ff12041a3bfb1fdf910e.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "549d9b89cbea362dc47752cd6e95c42fb19efc466206aed8a3723471a7906797", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ae42ee66038985a0580a372fe5d378dbf8a61660834ee2f8e1569bf0a8987062", "generation_seconds_batch": 23.940178786986507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1278351545333862, "target_z": 1.0859375040033834, "ce": 5.919358730316162, "genuineness": 4.394378662109375, "identity": 0.6610094308853149, "hypothesis": "Te he encontrado la cajita, estaba junto a la ventana vieja, podemos mirar juntos lo que hay dentro.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/549d9b89cbea362dc47752cd6e95c42fb19efc466206aed8a3723471a7906797.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": "54d0a9561b5b772e08a8eb6472cb6a00c897de7c87a1f04d4ba206d05254679f", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f0fbb6db3fc48815e3c7b2e2b0cb7e47ac29db417643cc8a2fcab5bb2cdb637e", "generation_seconds_batch": 24.797952094930224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40556833148002625, "target_z": 0.051025395670931194, "ce": 6.38003396987915, "genuineness": 4.645420074462891, "identity": 0.6137468814849854, "hypothesis": "Die Schlüsse liegen auf dem Küchentisch. Ich suchte in der Schublade, daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.14285714285714285, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/54d0a9561b5b772e08a8eb6472cb6a00c897de7c87a1f04d4ba206d05254679f.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "553f9e51a33772327bf31053821ec0659a0aebc683f234fe300dc9a97dbe4e90", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a0ac06c63fb6edcd05d0ecc11c1e942f6b47389015bccbb32559a4e37099ffeb", "generation_seconds_batch": 18.530412995023653, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2391010820865631, "target_z": -0.18749998932431086, "ce": 6.372091293334961, "genuineness": 4.607763767242432, "identity": 0.42908817529678345, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/553f9e51a33772327bf31053821ec0659a0aebc683f234fe300dc9a97dbe4e90.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "55dda83a68c1cb91c93613134cc5d4fb94d88b817e9e58757361842e31c7f891", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "12fae8592bfebb520224c17074ab07b2c4ff4a13d702b6c0dabd411e5088fcde", "generation_seconds_batch": 23.248191789956763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5110373497009277, "target_z": 0.20214844400549806, "ce": 6.157639026641846, "genuineness": 4.381826400756836, "identity": 0.5702798962593079, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/55dda83a68c1cb91c93613134cc5d4fb94d88b817e9e58757361842e31c7f891.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "55e068cbbc9d6a413c06a1247f2eb4a98ed451862857c9653e45a41dc36a615c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "5c458d09a736f1b14a83b96ab653b83a955769324a37874a9b0b6078d34717ad", "generation_seconds_batch": 25.246419003000483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19820840656757355, "target_z": -0.24609374399492487, "ce": 6.181467056274414, "genuineness": 4.469690799713135, "identity": 0.44860854744911194, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/55e068cbbc9d6a413c06a1247f2eb4a98ed451862857c9653e45a41dc36a615c.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "56e29da0752c3213c21d8e4f56c50afdc1d3341026dee64794f87d23986c0dd5", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5642362b8b1f2d237618c968ce62efae3ae5e5a0b19e24f4d02c81861297102b", "generation_seconds_batch": 24.85255292407237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9751691818237305, "target_z": 0.867187509341228, "ce": 6.284721851348877, "genuineness": 4.645420074462891, "identity": 0.6132453680038452, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/56e29da0752c3213c21d8e4f56c50afdc1d3341026dee64794f87d23986c0dd5.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "573fbe1bbb6187b00e99a8587017184d96ca8e6594d863dfe8dc000d64044e6a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6079e1f47c67b8547f967c6c103d1e305511e5c6e5445c93db1c54d50a0deb16", "generation_seconds_batch": 22.44120661902707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3058924376964569, "target_z": -0.091796877335307, "ce": 6.284721851348877, "genuineness": 4.532451152801514, "identity": 0.3498728275299072, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/573fbe1bbb6187b00e99a8587017184d96ca8e6594d863dfe8dc000d64044e6a.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "5790001b192155e8ef537e99cbe061632158bece4392911a4fed47daa8832eec", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "7276bb09fd19ec09179c9c2c7d095a0157c411f073636d57052dafa83dc184e7", "generation_seconds_batch": 24.49929645296652, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17639897763729095, "target_z": -0.27734374933276945, "ce": 6.09409761428833, "genuineness": 4.406930446624756, "identity": 0.6732012033462524, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5790001b192155e8ef537e99cbe061632158bece4392911a4fed47daa8832eec.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "57a95c5a7f8f65958e2fe926af7890885018652821234c50904407a4bfad67d1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a6243a14639079d24cc1251e64bd87575bb0bdcdc8363a5081bbabf69b613ee5", "generation_seconds_batch": 26.62664995295927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17912515997886658, "target_z": -0.2734374933276943, "ce": 5.780362129211426, "genuineness": 3.9801597595214844, "identity": 0.36358287930488586, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/57a95c5a7f8f65958e2fe926af7890885018652821234c50904407a4bfad67d1.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": "587681054061a59e896b8d0f437e73b871fe9a31c28021d49fbc3dca129a3ffb", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Tu mensaje llegó después de que me fuera.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lo leí dos veces... y guardé el teléfono.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ae74b019d8a588a1148cda4919daadc331c2f2c20ce09d50f1f4d9d93f1c5f06", "generation_seconds_batch": 23.187365590943955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9206455945968628, "target_z": 0.7890624746452383, "ce": 6.23706579208374, "genuineness": 4.469690799713135, "identity": 0.5411431789398193, "hypothesis": "Tu mensaje llegó después de que me fuera. Lo leí dos veces y guardé el teléfono. Dime cuándo podemos hablar.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/587681054061a59e896b8d0f437e73b871fe9a31c28021d49fbc3dca129a3ffb.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "587f3292395f7e1253d5fc6cedfc575b4394ca5e850e6862814a197d561ecc7a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "0d1575859fe6a88110c0df480d0c7d07557374c7392ed061173688aa3f2202ad", "generation_seconds_batch": 21.12887838797178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5771471858024597, "target_z": 0.29687502935814514, "ce": 6.403861999511719, "genuineness": 4.300237655639648, "identity": 0.5518478155136108, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/587f3292395f7e1253d5fc6cedfc575b4394ca5e850e6862814a197d561ecc7a.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "58ae050fd2481a7290bf8032d7ef73c2215816e1d78cb0960464d3e4846adc8f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "3a2c816527078fdb1cf4b2650335f0325195591be505ea1f6ac486d4552ee77f", "generation_seconds_batch": 24.990794991026632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8715744018554688, "target_z": 0.7187499946621554, "ce": 6.284721851348877, "genuineness": 3.9048471450805664, "identity": 0.3444232940673828, "hypothesis": "The 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_Relief/58ae050fd2481a7290bf8032d7ef73c2215816e1d78cb0960464d3e4846adc8f.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "58e93e2faf10847696f9648971cbdfc8dc49fec45d16031a46b25d88a735d980", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0fd8eb15f158ad6e0577ce6270ac633761ace8615bff027522e1ef17ea64e6ee", "generation_seconds_batch": 21.57926731801126, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2914059162139893, "target_z": 1.3203126080913525, "ce": 5.982900142669678, "genuineness": 4.086852550506592, "identity": 0.44518470764160156, "hypothesis": "Te he encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.058823529411764705, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/58e93e2faf10847696f9648971cbdfc8dc49fec45d16031a46b25d88a735d980.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "58ea25c98e3e0e917b31c12b7565c4f5941e76f79dea67ac3a794a985a59e110", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "efc0d8821a05b84dc0cf93870c0c9af7b7e309759e44a67c714ae50c43d8f0d9", "generation_seconds_batch": 18.94264407805167, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9697168469429016, "target_z": 0.8593750400338342, "ce": 6.316492557525635, "genuineness": 4.394378662109375, "identity": 0.791336178779602, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/58ea25c98e3e0e917b31c12b7565c4f5941e76f79dea67ac3a794a985a59e110.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "5929ace4887e3e19869679ba99fdadaf6a3ea29dc9ed50971f71769ce5fb62ef", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2922004952094ed35d3f33453545615f0f670e87afaaca4f5da82af2d66ceace", "generation_seconds_batch": 21.831020062905736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7270869612693787, "target_z": 0.5117187466638471, "ce": 6.197352409362793, "genuineness": 4.3504462242126465, "identity": 0.6318970322608948, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5929ace4887e3e19869679ba99fdadaf6a3ea29dc9ed50971f71769ce5fb62ef.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "596cbe7f7ff9bbeed22799302f55cc561656184856db62fbf0bec9187161247e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "e9bae061cc9fd3cd67141b64553888014ec49e804cac3d902a77a0f730d45bbf", "generation_seconds_batch": 22.052578244940378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4876906871795654, "target_z": 1.601562528023684, "ce": 6.078212261199951, "genuineness": 4.068024158477783, "identity": 0.6162132620811462, "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_Relief/596cbe7f7ff9bbeed22799302f55cc561656184856db62fbf0bec9187161247e.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "5a1d5d2467a7a36c0c33ea1ad0e0415c608a5ef222864fb45e05b4f88f116b58", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ce66bea7923cebeb752d026e4bba287a209eda0324d74bbf383685f61f7c0c84", "generation_seconds_batch": 18.91695726895705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15458954870700836, "target_z": -0.308593754670614, "ce": 6.149696350097656, "genuineness": 4.306513786315918, "identity": 0.679420530796051, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5a1d5d2467a7a36c0c33ea1ad0e0415c608a5ef222864fb45e05b4f88f116b58.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": "5a1f350bb4015c6fe78b2b8682735a73306d952172a2e95e53cec63bbbb1646b", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "548ec3377e1e2c2cbd32ac072a3dca4f3240135d943b96192c6c92412899ddd6", "generation_seconds_batch": 19.85053206095472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19548222422599792, "target_z": -0.25, "ce": 6.157639026641846, "genuineness": 4.400654315948486, "identity": 0.690955638885498, "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_Relief/5a1f350bb4015c6fe78b2b8682735a73306d952172a2e95e53cec63bbbb1646b.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": "5af4f812dd77b1cdbe1772514ae5cb20e77d040a47023c6acc0e429c62dc0a57", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d4a8cd22a93ed3eaabe6f61de38ec51048d9af7fd25fc1bc811521efc035df6d", "generation_seconds_batch": 24.079575496027246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.224788635969162, "target_z": -0.20800781733742163, "ce": 6.252951145172119, "genuineness": 4.519899368286133, "identity": 0.7312747240066528, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5af4f812dd77b1cdbe1772514ae5cb20e77d040a47023c6acc0e429c62dc0a57.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "5b1420d5c93ffb59495704ef223b5909f217a2d63dd31003f4eb019ad79cc7a6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "7c74c22b1ca713724e60cf5938972d07a48f4229895b29143c293830a4110ecd", "generation_seconds_batch": 21.174144941032864, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0787639617919922, "target_z": 1.0156250240203006, "ce": 6.1020402908325195, "genuineness": 4.65797233581543, "identity": 0.7185270190238953, "hypothesis": "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_Relief/5b1420d5c93ffb59495704ef223b5909f217a2d63dd31003f4eb019ad79cc7a6.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "5b8f3b00067b67199c3d97d90d5a4b45f925e0ecb8fdd4ec64aa9f7dc55ae3b4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a5f5454494895f94728d1b1885f1b730aff6d8ef23f009e28226f057a1a85fd3", "generation_seconds_batch": 23.588919047964737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6343969106674194, "target_z": 0.37890625600507516, "ce": 5.613565921783447, "genuineness": 3.9173994064331055, "identity": 0.46454164385795593, "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_Relief/5b8f3b00067b67199c3d97d90d5a4b45f925e0ecb8fdd4ec64aa9f7dc55ae3b4.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "5b97202e33d8bf1b09685e6d24e9065a442540c324321a23eb88f9a84e3e1021", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "8b9ffd0ef6db5093e0b2b60f6bf0ad81aeb81bca05e60d11ad1365083680eaad", "generation_seconds_batch": 24.832552770036273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30827784538269043, "target_z": -0.08837890599978854, "ce": 5.895530700683594, "genuineness": 4.3881025314331055, "identity": 0.064580999314785, "hypothesis": "De deur 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_Relief/5b97202e33d8bf1b09685e6d24e9065a442540c324321a23eb88f9a84e3e1021.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": "5c0685b5936674809beecbfb74dc9565458b3777fd79a20c804d1f005e5a5484", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We zetten het na de lunch terug.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Natural clear speech.) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Natural clear speech.) [3.2 seconds duration] We zetten het na de lunch terug.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "653928a3fb26e3c1c230ec715efee76b7f3803ecc20e0b5bbe6785b99b25a405", "generation_seconds_batch": 16.7769504430471, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.305551677942276, "target_z": -0.0922851406534854, "ce": 6.149696350097656, "genuineness": 4.381826400756836, "identity": 0.7108185887336731, "hypothesis": "Iemand heeft het kleine blauwe stoeltje verplaatst. Het stond hier naast de hoge boekenkast. We zetten het naar de lunch terug.", "wer": 0.047619047619047616, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5c0685b5936674809beecbfb74dc9565458b3777fd79a20c804d1f005e5a5484.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "5c14fe94ecee8db5232fecdd7581112b48040d201ca2cd107af3dead2e7740e5", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fd325a0c48fbfacb8800deef77670b70577d74d059ea5bbed222f33323a053b0", "generation_seconds_batch": 24.76645421795547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18730369210243225, "target_z": -0.26171874666384715, "ce": 6.1894097328186035, "genuineness": 4.356721878051758, "identity": 0.5893568396568298, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5c14fe94ecee8db5232fecdd7581112b48040d201ca2cd107af3dead2e7740e5.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "5c3e99da7dc2bbdcc49a96531cdc6fa1cd5ddbe8467f8af670861f3ca63d84f3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "53586dbbfbc753678f6722d078b7c4d0b36d8088825ff1090a91dbeda46ed943", "generation_seconds_batch": 23.614297808962874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7734320163726807, "target_z": 0.5781250346959896, "ce": 6.165581703186035, "genuineness": 3.6663577556610107, "identity": 0.3219788074493408, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5c3e99da7dc2bbdcc49a96531cdc6fa1cd5ddbe8467f8af670861f3ca63d84f3.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "5c5812ee9afc76803cbd2788bff232c84a61e652fd5ea8508383461cab2861ed", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "30ba8f337cdcd7f619f1b7c66a944aa5326a9bfbdbff1395fd6ef5093ee2ec43", "generation_seconds_batch": 20.010627805953845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11914923787117004, "target_z": -0.3593749973310777, "ce": 6.221180438995361, "genuineness": 4.413206577301025, "identity": 0.6937159299850464, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5c5812ee9afc76803cbd2788bff232c84a61e652fd5ea8508383461cab2861ed.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "5c95ace7f46722413e7dd8ca6831364be72c5cd11e589514f8c716d09107a9e8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5e58fac6a36ab5f82eba5883a38cb468357e47bae73495c75bf22353a78f051d", "generation_seconds_batch": 18.771195524022914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30895939469337463, "target_z": -0.08740233666067518, "ce": 6.125868320465088, "genuineness": 4.300237655639648, "identity": 0.7227730751037598, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5c95ace7f46722413e7dd8ca6831364be72c5cd11e589514f8c716d09107a9e8.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "5cc5fcfc485ca54f25165477fd0281b3a33e9257d75d6d9301504b3057261f4b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cd9eadf2082e8c19fa2a9ef11ad884430a00218bf55d881b87c698a87d43919c", "generation_seconds_batch": 30.356426057987846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4830940365791321, "target_z": 0.1621094000211464, "ce": 6.006728172302246, "genuineness": 3.961331605911255, "identity": 0.5109614133834839, "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_Relief/5cc5fcfc485ca54f25165477fd0281b3a33e9257d75d6d9301504b3057261f4b.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "5d1d1aa2dfed6f2d24d759a36399437933b262270df7577c791125e526336fb4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e034b111f6a62943bc98c52a16ab1ceef3775e7332c63af988fd105a93b7df4c", "generation_seconds_batch": 26.132597391027957, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3931301534175873, "target_z": 0.033203144016071266, "ce": 6.316492557525635, "genuineness": 4.494794845581055, "identity": 0.3684139549732208, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5d1d1aa2dfed6f2d24d759a36399437933b262270df7577c791125e526336fb4.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "5dae4aa012784dda41bd674ff3471a488ec10e348c2f15df95997f8e42dddd82", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "6991bfc8108c6f0d845929468dc383d7551002dd49500b62c3bf4ff007af9a02", "generation_seconds_batch": 21.56574918399565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4261850416660309, "target_z": 0.08056639398963826, "ce": 6.1894097328186035, "genuineness": 4.507347106933594, "identity": 0.7143468856811523, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5dae4aa012784dda41bd674ff3471a488ec10e348c2f15df95997f8e42dddd82.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "5dc78c8a48bf018fdbd4ef86a63429df2b43db5c190140cef386fca8b3f069d1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5fa894951dfdaa1fb0746f368671735ae5d2015de4dc96f6fb825a98fe3c5986", "generation_seconds_batch": 16.353198898024857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1804882436990738, "target_z": -0.27148437600084585, "ce": 6.022613525390625, "genuineness": 4.18726921081543, "identity": 0.4532177448272705, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5dc78c8a48bf018fdbd4ef86a63429df2b43db5c190140cef386fca8b3f069d1.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "38915de8f8a7398b26bab9cac4e7e4cdab78d761d560a483869ff543ef7312bf", "generation_seconds_batch": 18.5264182779938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30930015444755554, "target_z": -0.08691407334249678, "ce": 6.197352409362793, "genuineness": 4.570107460021973, "identity": 0.8129485845565796, "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_Relief/5e0af124ad7421917e897f2876d49b25e213a1bc87e01fe43f09b9c255c2a32f.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "5ec5ebeb0bfddacc8f314ec57a5d23d6169de48a1156bd9ac6451a10a5fd19e4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 129, "seconds_generated": 10.32, "mp3_sha256": "b5ef72db1a502910d87e1131d02a7113cb72d89930e0f0442c8430d7f1c44ea9", "generation_seconds_batch": 23.742844113963656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.3109965324401855, "target_z": 2.7812500907433577, "ce": 5.903473377227783, "genuineness": 4.124508857727051, "identity": 0.4740578532218933, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'a", "wer": 0.10526315789473684, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5ec5ebeb0bfddacc8f314ec57a5d23d6169de48a1156bd9ac6451a10a5fd19e4.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "5f63a3e8fcdf78b494f5faa67d96ad112324cd3e8e1fbd31fe3a6f2e76be3bcd", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5836d198693ef39a3ae7651431e96ed4e22106e9749375d7c5aea9fc7831ea56", "generation_seconds_batch": 25.157097224029712, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5124004483222961, "target_z": 0.20410158268372477, "ce": 6.38797664642334, "genuineness": 4.143336772918701, "identity": 0.5377060174942017, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5f63a3e8fcdf78b494f5faa67d96ad112324cd3e8e1fbd31fe3a6f2e76be3bcd.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": "5f6f964bce2a4134f89c3804ad1c998258e6c97170282c0bc3392e7e4c4ac226", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4e4ebc796d1aa45fe5611a4aa7954245f041e466bda28e6d55aec8968e52383a", "generation_seconds_batch": 17.606630170019343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5585713386535645, "target_z": 1.7031250560473679, "ce": 6.3641486167907715, "genuineness": 4.582659721374512, "identity": 0.6151487231254578, "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_Relief/5f6f964bce2a4134f89c3804ad1c998258e6c97170282c0bc3392e7e4c4ac226.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "5f85bc7c75f57272eae5c7687c45f22763a3e848e59094c9a95e7ab892d39c2c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "748259b1312f3d602046bf7fa9ae4cb3731c5d71f75c0d780ab05d42bbd56f69", "generation_seconds_batch": 17.878418394946493, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4939987361431122, "target_z": 0.17773438133869043, "ce": 6.070269584655762, "genuineness": 3.6067352294921875, "identity": 0.2037985622882843, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/5f85bc7c75f57272eae5c7687c45f22763a3e848e59094c9a95e7ab892d39c2c.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "604018666812db5a90ad3c99fd4cc602482a994c17e5f8e1f3752d0d7d40eeca", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "023f5354ef1da17c0e1dd8e8d65a53f0a6054875ff402d331e0f055082eb184e", "generation_seconds_batch": 17.668190366006456, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8966174125671387, "target_z": 2.187500032027067, "ce": 6.3641486167907715, "genuineness": 4.18099308013916, "identity": 0.6363891363143921, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble.", "wer": 0.15789473684210525, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/604018666812db5a90ad3c99fd4cc602482a994c17e5f8e1f3752d0d7d40eeca.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "6096d33ea705b611dcc76734f08ea58700a7e2b6398e2ed156408c9fb5991a1b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9caeda71ef41743b040d99d14f20c267eaec92291f86ca7d9de240aae9c16178", "generation_seconds_batch": 22.303796604974195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37745460867881775, "target_z": 0.010742177324733796, "ce": 5.927301406860352, "genuineness": 4.168440818786621, "identity": 0.3710712492465973, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6096d33ea705b611dcc76734f08ea58700a7e2b6398e2ed156408c9fb5991a1b.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "60ecace6342cc5b89ccfa4416090113e9ef461067c4d6573f03dcfa8aa6496ea", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "142d68c08ace90049d87a362fd3fcd908b2fd41d13b460705f6ce2386ca059da", "generation_seconds_batch": 17.453031396958977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8524911403656006, "target_z": 0.6914062239780078, "ce": 6.252951145172119, "genuineness": 3.8671910762786865, "identity": 0.445451021194458, "hypothesis": "The 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_Relief/60ecace6342cc5b89ccfa4416090113e9ef461067c4d6573f03dcfa8aa6496ea.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "613e4ab0b043a254dbdf823791a72f6d7c548790e9100894607f88a223add43c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3743d89bd8810e7f2295b2c86059e85ae93c773ca20e32c9b3b664bbe9bb03bd", "generation_seconds_batch": 23.428426111931913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.583962619304657, "target_z": 0.30664063734376557, "ce": 6.324435234069824, "genuineness": 4.494794845581055, "identity": 0.5228056311607361, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/613e4ab0b043a254dbdf823791a72f6d7c548790e9100894607f88a223add43c.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "61619e4aed515b0fa09f5f861606f5c5a4f20c7d9304729c2882a0aaea4e67cb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 131, "seconds_generated": 10.48, "mp3_sha256": "be705aedb27d648d9c620d933ecc1bf35dd3bfb9f403088462b13fec173aa095", "generation_seconds_batch": 25.586160354083404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1987158060073853, "target_z": 1.1875000320270674, "ce": 5.95112943649292, "genuineness": 3.9048471450805664, "identity": 0.5629525184631348, "hypothesis": "La puerta sigue abierta y dejado tu abrigo sobre la silla, dime cuándo, Neh.", "wer": 0.2, "duration_error_s": 0.28000000000000114, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/61619e4aed515b0fa09f5f861606f5c5a4f20c7d9304729c2882a0aaea4e67cb.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "63ae574c960e542d527c3718471d326a0158b5d7823f76dfd316eef18e88f981", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a55475a87026bb4b171ce4c2f6c37342a41e40cd105aba0a6996305f49b7cd78", "generation_seconds_batch": 18.771195524022914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37949925661087036, "target_z": 0.013671885342073847, "ce": 6.165581703186035, "genuineness": 4.406930446624756, "identity": 0.5778487920761108, "hypothesis": "Ik 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_Relief/63ae574c960e542d527c3718471d326a0158b5d7823f76dfd316eef18e88f981.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "63d00712ef385049d82e5afa5bf6c99dcc920f6f5761b13d54cbac9d15ba47db", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "798fe7c48c9d785b57f87ae36693a852600b43ffa7bb4868669b45fc382912a2", "generation_seconds_batch": 23.966249189921655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1169304847717285, "target_z": 1.0703125653885959, "ce": 6.260893821716309, "genuineness": 4.080576419830322, "identity": 0.4656708240509033, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/63d00712ef385049d82e5afa5bf6c99dcc920f6f5761b13d54cbac9d15ba47db.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "6491fc99c3feb3e7c78552d5d67a7a20852f0d02afded4e5e1f934d720b21b38", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ba0160b8435ca82acf978583723e9747dc72543b246097e058ecaaf4ccb406c8", "generation_seconds_batch": 17.252934913965873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0378713607788086, "target_z": 0.9570313761065778, "ce": 5.95112943649292, "genuineness": 4.030367851257324, "identity": 0.6197168827056885, "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_Relief/6491fc99c3feb3e7c78552d5d67a7a20852f0d02afded4e5e1f934d720b21b38.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "653677cd6900536d32f680fef7b0ce7304e8872dd3a85feb4d34bce5a7afa144", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "489931a5b60eb9a1037e6b2433c03c8247820608519bac69f66cbc00e3fa1424", "generation_seconds_batch": 19.03732377209235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5258572101593018, "target_z": 1.6562500693919793, "ce": 6.229123115539551, "genuineness": 4.406930446624756, "identity": 0.5380579829216003, "hypothesis": "I've trouved the petite boîte. Elle était près de la vieille fenêtre. We'll regard ensemble what it contained.", "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_Relief/653677cd6900536d32f680fef7b0ce7304e8872dd3a85feb4d34bce5a7afa144.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": "6553509c27d9136f84598b0b91858f8c57f3002d4cc975b451effa62d19fd531", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Iemand heeft het kleine blauwe stoeltje verplaatst.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond hier... naast de hoge boekenkast.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6aa144542b2ee5c354741cf5977bd779be63f961b013d7b9a05e75077b8db8ce", "generation_seconds_batch": 24.079575496027246, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2377379834651947, "target_z": -0.18945312800253758, "ce": 6.284721851348877, "genuineness": 4.557555198669434, "identity": 0.5717250108718872, "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_Relief/6553509c27d9136f84598b0b91858f8c57f3002d4cc975b451effa62d19fd531.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "65b2acce725dda022f1100ac9059be21b65ed277ae4cace4b3893e469b632d13", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b9d0f0e2d4708a9a98cbd331dcdce00f2740ae435bd2cf4dd4b19e5aca2c9963", "generation_seconds_batch": 23.425523838959634, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5389806628227234, "target_z": 0.24218748798984974, "ce": 6.316492557525635, "genuineness": 4.325342178344727, "identity": 0.3649166226387024, "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_Relief/65b2acce725dda022f1100ac9059be21b65ed277ae4cace4b3893e469b632d13.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "65f96dc9e896ee99aef44766d1bc75b6b06c35870e9d044125d34660275c4ac5", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ccb6198c06b506b393613aeeae9928c5e329c3818a04d163561502e07a037bdc", "generation_seconds_batch": 21.99052685010247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38444045186042786, "target_z": 0.020751959672199977, "ce": 6.197352409362793, "genuineness": 3.898571252822876, "identity": 0.5298129320144653, "hypothesis": "La puerta sigue abierta y he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/65f96dc9e896ee99aef44766d1bc75b6b06c35870e9d044125d34660275c4ac5.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "664bd45cb79c0c1d8f8192c9cb2559904e028cab6e4947d45b3d5cda93960fff", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "63481e241eb7ab6609d7fb67a85af28cf90f9a0811f953373ababb957749e499", "generation_seconds_batch": 28.154039929038845, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9997047781944275, "target_z": 0.9023437493327694, "ce": 5.6413655281066895, "genuineness": 4.494794845581055, "identity": 0.7234816551208496, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/664bd45cb79c0c1d8f8192c9cb2559904e028cab6e4947d45b3d5cda93960fff.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "66eca9364357eda032e879862cb44944dfdbc2389074c5020b2020b60fef3249", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0f79e895fd3c3dcdca60d3f758c3a288ea97bef8cc2bc8c400477e326630410b", "generation_seconds_batch": 21.630254888907075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2704521417617798, "target_z": -0.14257809864439244, "ce": 6.1020402908325195, "genuineness": 4.306513786315918, "identity": 0.3991276025772095, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/66eca9364357eda032e879862cb44944dfdbc2389074c5020b2020b60fef3249.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "671e02559cf538fe12e9565cf07d64fbc0578959744ab6ab97a92f1e630e9164", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c1d0e8c441bf7d589c9ac322a02f362c9dcb303fb0fd7110c860d15ebf615640", "generation_seconds_batch": 25.366173141053878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25409504771232605, "target_z": -0.1660156346748433, "ce": 6.181467056274414, "genuineness": 4.3881025314331055, "identity": 0.6756606698036194, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/671e02559cf538fe12e9565cf07d64fbc0578959744ab6ab97a92f1e630e9164.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "674b2f44f36d677cb77a6ad6e1e2b3de656b0eda607262308092dd089a94ed3c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4856c57728e74f9587ca6f2bbcd9fe790f5211a7a9f8ae5e65c6f0ad56d3fdfe", "generation_seconds_batch": 25.20946493104566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.046905517578125, "target_z": -0.46289062133023184, "ce": 5.967014789581299, "genuineness": 3.9676074981689453, "identity": 0.46689870953559875, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/674b2f44f36d677cb77a6ad6e1e2b3de656b0eda607262308092dd089a94ed3c.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "679666511645678a7c54d7f04852db933523bad898aab262d2d2868e404e1d2a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "8222ca86646cb23001876c73e0eb9b1e1d6fcae5fd5da35890b49f7efd58d64a", "generation_seconds_batch": 19.27401447307784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3023104667663574, "target_z": 1.3359373758951139, "ce": 6.435632705688477, "genuineness": 4.457139015197754, "identity": 0.271298885345459, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/679666511645678a7c54d7f04852db933523bad898aab262d2d2868e404e1d2a.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": "67ec043ecf11d0e1aa4692a6972cff28617d08eed6afed2e790fb52c5e6bbe53", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ab0728a973784cfe36c82535d2aab0c0e5076d7ed6210642338943170cd32d4c", "generation_seconds_batch": 19.39999489299953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.498088002204895, "target_z": 0.183593754670614, "ce": 5.982900142669678, "genuineness": 4.319066047668457, "identity": 0.6498059034347534, "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_Relief/67ec043ecf11d0e1aa4692a6972cff28617d08eed6afed2e790fb52c5e6bbe53.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "67f8c045da448f3cbd7a8752d18cc46aed72eff38fbb2209ea98f92730ff8728", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b21fdcccda324f9e980d5fa1fe0b00f911f660258bc5c186e14cc13d0672eb0", "generation_seconds_batch": 23.1959709119983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7761582136154175, "target_z": 0.5820313120524431, "ce": 5.7406487464904785, "genuineness": 3.8420867919921875, "identity": 0.6039221882820129, "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_Relief/67f8c045da448f3cbd7a8752d18cc46aed72eff38fbb2209ea98f92730ff8728.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": "6838e96db9af76a16742022717132934d4b7d9d2059919deb8c5fdcfa4c2d556", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9631a86e7ae6c614a6970a1232f089da2aeae24299c1377f21cddde3fd6074e0", "generation_seconds_batch": 17.383736678981222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.1801400184631348, "target_z": 2.5937501441218034, "ce": 6.23706579208374, "genuineness": 4.319066047668457, "identity": 0.6940789222717285, "hypothesis": "Ton message est arrivé après mon départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6838e96db9af76a16742022717132934d4b7d9d2059919deb8c5fdcfa4c2d556.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "686bbc1fbeacad0b47d4e79ccb1e6c4b36bee61c17b16413c4887d5aaac46c12", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "49858c567056072d6bf8ae405dc075e9a784ecdeb1a6c6b5bb44dc980b6239e8", "generation_seconds_batch": 26.132411172031425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1464110165834427, "target_z": -0.32031250133446115, "ce": 6.205295085906982, "genuineness": 4.406930446624756, "identity": 0.5007718801498413, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/686bbc1fbeacad0b47d4e79ccb1e6c4b36bee61c17b16413c4887d5aaac46c12.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "68997cad2aa9edbf9fa7a0a9d7d088cea9e4cd5da0b3f55365319b324096249b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "68f36c5512467e3808b16e6a4b37c8d6ae2a9c9c877d903d6dee793f74ad17bb", "generation_seconds_batch": 22.094615316949785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3079370856285095, "target_z": -0.08886716931796694, "ce": 6.133810997009277, "genuineness": 4.432034492492676, "identity": 0.19115306437015533, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/68997cad2aa9edbf9fa7a0a9d7d088cea9e4cd5da0b3f55365319b324096249b.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": "68c60a1f5b78f0622799a4b4215bcd7b510ade9e4226352c812bd2ab6e3e6875", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6e0ffd97b657f3122c4813602e80ac99887b819497b443be696105869f4f34e3", "generation_seconds_batch": 25.435752124991268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8770267367362976, "target_z": 0.7265624639695492, "ce": 6.395919322967529, "genuineness": 4.193545341491699, "identity": 0.3383219838142395, "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_Relief/68c60a1f5b78f0622799a4b4215bcd7b510ade9e4226352c812bd2ab6e3e6875.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "69096d3acb52e08c461e4739b6d34327efaef94861ecf7f75cee9cc7a8dff0b3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f82df31f939fe2b223e27b58ed8ad7f35de462205001e8a41222db1f5db542ab", "generation_seconds_batch": 29.61819564900361, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2363748997449875, "target_z": -0.191406245329386, "ce": 5.998785495758057, "genuineness": 4.2374773025512695, "identity": 0.4571859538555145, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/69096d3acb52e08c461e4739b6d34327efaef94861ecf7f75cee9cc7a8dff0b3.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "69475eb237be59dc3301c0ad253edf7fa8794b668fdfa3726eee73c1f32aa449", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "c3167b459bb9c03d14fd33588d2fac309a495540fa52bd204e6d2a5f8f2a3fd9", "generation_seconds_batch": 21.91708782291971, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2968581914901733, "target_z": 1.3281249919932332, "ce": 6.205295085906982, "genuineness": 4.281409740447998, "identity": 0.8091468214988708, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/69475eb237be59dc3301c0ad253edf7fa8794b668fdfa3726eee73c1f32aa449.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "69ec8c56c3df48604b6601ca778368cba42968a9c7f7c2e0e63c12c063efa739", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "586689c49150145fe0356f64060309b14509d4758ab8491b77739489f0f88140", "generation_seconds_batch": 27.875174573040567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6725634336471558, "target_z": 0.4335937973733705, "ce": 6.38797664642334, "genuineness": 4.231201171875, "identity": 0.6000128388404846, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/69ec8c56c3df48604b6601ca778368cba42968a9c7f7c2e0e63c12c063efa739.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "6a01c68ae2a478fc417eaaa55d626bee524ad5371e8bc019f0f834bbbe60892f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f90dd08464ca2a817511d5598c05b8fc500b45a6e7d3bf4e2fc393a46530ab0f", "generation_seconds_batch": 21.935717694927007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0296926498413086, "target_z": 0.9453123732261915, "ce": 6.141753673553467, "genuineness": 4.356721878051758, "identity": 0.7844780087471008, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6a01c68ae2a478fc417eaaa55d626bee524ad5371e8bc019f0f834bbbe60892f.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "5f7dd2c595ead4082c17a9c702bec163561173ac4fb4ad2eb97aa754946e988a", "generation_seconds_batch": 18.357007098034956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4265258312225342, "target_z": 0.0810547000105732, "ce": 6.332377910614014, "genuineness": 3.9425034523010254, "identity": 0.2900169789791107, "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_Relief/6a61bc20d43b3e97640d8dd45682f7055c5dbaa5aa987cdb55f8a7d7a432a2c2.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": "6aab9ce25aa4ed8cb022ac18434eec83bbdef2aa3df950ccfd5adf8b96a71a92", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7af4825a3cb5780e4c38e6c6fcbc982314825b9359ab303e7642b4e9affa66d7", "generation_seconds_batch": 17.468088551075198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4190288186073303, "target_z": 0.07031247998308288, "ce": 6.395919322967529, "genuineness": 4.362998008728027, "identity": 0.18807141482830048, "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_Relief/6aab9ce25aa4ed8cb022ac18434eec83bbdef2aa3df950ccfd5adf8b96a71a92.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "6ac01d4fde2b2e50e52469abd51684b31188fdd7b8207db652b9bd8546ba27c7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "59f3d6167548207647b014abbe0a1a5a515cf054ea27d024fac78a0414edb95c", "generation_seconds_batch": 19.919616841012612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5294390320777893, "target_z": 0.22851560264777587, "ce": 6.324435234069824, "genuineness": 4.457139015197754, "identity": 0.6562668681144714, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6ac01d4fde2b2e50e52469abd51684b31188fdd7b8207db652b9bd8546ba27c7.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "6b2ceb26c7a3de06611f4eb0747220e3408350ae9caf7f8db7d359eb7e73a634", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc052e3916e982dc0c5e11c01b2cdb7e94c6ec87d0c06d96f76762f3d4527424", "generation_seconds_batch": 19.137854815926403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.74344402551651, "target_z": 0.5351562399915414, "ce": 6.221180438995361, "genuineness": 4.268857479095459, "identity": 0.4288756847381592, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6b2ceb26c7a3de06611f4eb0747220e3408350ae9caf7f8db7d359eb7e73a634.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "ef3582d42e1c5b681e8114675f4505f817c4c000657f49fca1e9293c4f415f41", "generation_seconds_batch": 16.89829314209055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27794909477233887, "target_z": -0.13183596402241518, "ce": 6.165581703186035, "genuineness": 4.595211505889893, "identity": 0.571641743183136, "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_Relief/6b973c750e3616c70f28663c29496a0c74bea4a87dff4bad65cadc5394b99131.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "6c085c3eaf4f7f7dee315b802a3f7cf0d961b2ba26782a87ca83345a24d5b9f4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c72860ea80196feb2451377bf1ddfd08d03dc57786e3e65eeaaaee0916944844", "generation_seconds_batch": 23.260567906079814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0351450443267822, "target_z": 0.9531249279390983, "ce": 6.1894097328186035, "genuineness": 4.281409740447998, "identity": 0.7808200716972351, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6c085c3eaf4f7f7dee315b802a3f7cf0d961b2ba26782a87ca83345a24d5b9f4.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "6c1575ab1d08982960d7e72e752c5e66509b4410f8264ec2b90cd82871369698", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "30a1ec01818bb51e56af32d8ce4444cba62c0e5af095414b7af4205ef53f2f5b", "generation_seconds_batch": 24.876981231034733, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.147425889968872, "target_z": 2.5468751574664146, "ce": 6.070269584655762, "genuineness": 4.281409740447998, "identity": 0.3528771996498108, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6c1575ab1d08982960d7e72e752c5e66509b4410f8264ec2b90cd82871369698.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": "6c48f1f999cf444317faceb597af03ca86fad9035783339bd0141cc12cb4b143", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e3556caf4f1d10426d38ea176b2531da8251c5e29746227d9f537c3d377aefa2", "generation_seconds_batch": 18.647716079023667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6916466355323792, "target_z": 0.4609374826520052, "ce": 6.308549880981445, "genuineness": 4.406930446624756, "identity": 0.33084744215011597, "hypothesis": "Die Schlüssel liegen auf dem Küchentisch. Ich suchte in der Schublade daneben dem Fenster. Nimm sie mit, wenn du gehst.", "wer": 0.09523809523809523, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6c48f1f999cf444317faceb597af03ca86fad9035783339bd0141cc12cb4b143.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "6c705aae8f67b572e4987d1fd942e845bb77ce9fedbcdec741c8126d1bbe711f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "435a35d39d979180adabd0ba2aed0c5c333544c4832eb32087f5f6dc796a487f", "generation_seconds_batch": 25.639295003958978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1878111362457275, "target_z": 1.17187509341228, "ce": 5.470598220825195, "genuineness": 3.810706615447998, "identity": 0.39191734790802, "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_Relief/6c705aae8f67b572e4987d1fd942e845bb77ce9fedbcdec741c8126d1bbe711f.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": "6d154fa9cdeb951302437612528460d2a69be079b4e68c9bffc0dd8cdeac07e4", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "921703beebbee76e0e8834701033cfcbf0192a5872dcb919a5d8dbdedf17112a", "generation_seconds_batch": 16.13522686099168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7379916906356812, "target_z": 0.5273437706841477, "ce": 6.197352409362793, "genuineness": 3.7542223930358887, "identity": 0.20543478429317474, "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_Relief/6d154fa9cdeb951302437612528460d2a69be079b4e68c9bffc0dd8cdeac07e4.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "6d8a163628df9721254ad558d29e8cbca5d4249a1f0c07dbd4d050e67eec3bb8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "7b5a46bdad1f5e146f6de661473dc54fc8a542dabedec301b02e27f75b92f86b", "generation_seconds_batch": 20.910176348988898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.74344402551651, "target_z": 0.5351562399915414, "ce": 6.316492557525635, "genuineness": 4.15588903427124, "identity": 0.29704341292381287, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6d8a163628df9721254ad558d29e8cbca5d4249a1f0c07dbd4d050e67eec3bb8.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "6d987c625b4c82c1fcd316f40ca350b2aed6d08a662b0bc7f91b2d395477cd31", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c946d184a53003478d34b0910accf83b1eb79a328f621230feb6329aa9347c7f", "generation_seconds_batch": 24.41722085198853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9370026588439941, "target_z": 0.8124999679729326, "ce": 6.308549880981445, "genuineness": 3.7416701316833496, "identity": 0.3792662024497986, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6d987c625b4c82c1fcd316f40ca350b2aed6d08a662b0bc7f91b2d395477cd31.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": "6e0f0291dfca58ea8294a039ebdc216bc368370cc4e42672668222c63f3d58aa", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7a9a50e3b149fd5fc45b5aa7d5f1f7d16bd538ea84601f868d16aa382a93d032", "generation_seconds_batch": 21.40804526908323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5757840871810913, "target_z": 0.2949218906799184, "ce": 6.173524379730225, "genuineness": 4.243753433227539, "identity": 0.7080669403076172, "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_Relief/6e0f0291dfca58ea8294a039ebdc216bc368370cc4e42672668222c63f3d58aa.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "6e117d4f07092c838777f53eca8644aaf5765c63503635828d56e8fd1a811424", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "b1ad7bed4fb99219dfe0e9f525812ab7218b71d760bfe759f3be46331362cd7a", "generation_seconds_batch": 26.02227647602558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6453015804290771, "target_z": 0.39453119461986264, "ce": 6.197352409362793, "genuineness": 3.9927117824554443, "identity": 0.44608384370803833, "hypothesis": "The 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_Relief/6e117d4f07092c838777f53eca8644aaf5765c63503635828d56e8fd1a811424.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "6e8a52e6680d0c3d886a182120c82c80b9b0d250293217789c6699a592d5daa9", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ab6b268c55f391b675262b9361baa46ebbc6a4f20b60c1739814a5f7fc54db8b", "generation_seconds_batch": 27.049043647013605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9833477139472961, "target_z": 0.8789062560050751, "ce": 6.09409761428833, "genuineness": 4.331617832183838, "identity": 0.7213298082351685, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6e8a52e6680d0c3d886a182120c82c80b9b0d250293217789c6699a592d5daa9.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "6ea01215b547fc4e02a7ee836e08e522dda0dd63fdf12f02dc1f151403257350", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "1612f2131de101d46dc13383b0fa91b2364cb26199092bb5a8cd3e532ccafa85", "generation_seconds_batch": 29.114267172990367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.907522201538086, "target_z": 2.203125141452881, "ce": 6.316492557525635, "genuineness": 4.256305694580078, "identity": 0.31179943680763245, "hypothesis": "I found the little box. It was beside the old window. We can look inside together?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6ea01215b547fc4e02a7ee836e08e522dda0dd63fdf12f02dc1f151403257350.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "6eb16221623b87617f95f93d487d071dda660336d592eb7b34759431e97e2f18", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "b868877cfbd68a0db6367de5d9954a09b5dd7d9bddd0bd85cfdef350d4a03d95", "generation_seconds_batch": 27.934305061004125, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28953537344932556, "target_z": -0.1152343706630013, "ce": 6.252951145172119, "genuineness": 4.457139015197754, "identity": 0.7464818954467773, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6eb16221623b87617f95f93d487d071dda660336d592eb7b34759431e97e2f18.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "6ec99cdcf1441a2fae27af50e67ec4de0e9d1fd2ebc92503c6bd1578e5e35f58", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "e9cf958c145e82fc85ac1dcabe477062e8cac7c3c70d83b35f518ef8e6078845", "generation_seconds_batch": 22.29736952704843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9838550090789795, "target_z": 2.3124998825674195, "ce": 6.133810997009277, "genuineness": 4.469690799713135, "identity": 0.7055457830429077, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what it contiens?", "wer": 0.3157894736842105, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6ec99cdcf1441a2fae27af50e67ec4de0e9d1fd2ebc92503c6bd1578e5e35f58.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "6f31c6bad39ec39480ae24c144132e136978c927f3228c8bebaea2bcf78fcfc2", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "800b6c05e6ebab52f56b94fb6a1e29e71d80f3c4a8e495d2c5066e3dacf14924", "generation_seconds_batch": 23.97468792705331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47968629002571106, "target_z": 0.15722655332557964, "ce": 6.3641486167907715, "genuineness": 4.218649387359619, "identity": 0.2591215670108795, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6f31c6bad39ec39480ae24c144132e136978c927f3228c8bebaea2bcf78fcfc2.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "6fbaf0680b0f59be67b08ac607ff00a850d7b107c0c501cbae1484192dce77ea", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f6f5028ff30a663b451634a4e3d923c3f5153024cb65eeb25a805ac0f93074d6", "generation_seconds_batch": 21.045565478969365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15458954870700836, "target_z": -0.308593754670614, "ce": 6.1020402908325195, "genuineness": 4.243753433227539, "identity": 0.525390088558197, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6fbaf0680b0f59be67b08ac607ff00a850d7b107c0c501cbae1484192dce77ea.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "6ff4dcd97586c43662a4bbf151be1dd80d5f64e17f9e75d0fa76a58487efb6b4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "07c2f4be80c67363bcdaf9f01e0d5467effff2a239cfbf0a395af51cf85f1583", "generation_seconds_batch": 28.10063522204291, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5301206111907959, "target_z": 0.22949221468964576, "ce": 6.268836498260498, "genuineness": 4.055472373962402, "identity": 0.1872064173221588, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/6ff4dcd97586c43662a4bbf151be1dd80d5f64e17f9e75d0fa76a58487efb6b4.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "70282edddc34a4caab01722f11aafc611aeb8bb7756d3eaeca890e00e8bbf0a5", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8e7b54cbf6fab9933590e1dafdad22a0fc403aa83f0b6b01e7f0f4298dcf4801", "generation_seconds_batch": 23.84896593890153, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.776665449142456, "target_z": 2.015624853209274, "ce": 6.284721851348877, "genuineness": 4.381826400756836, "identity": 0.7972344756126404, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/70282edddc34a4caab01722f11aafc611aeb8bb7756d3eaeca890e00e8bbf0a5.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "709e911686369fa7385618b442be5b66b96f3cbb261c618b8351a5500589b08c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "159ddc05586b5ad758a27a6dccfa431081132cccf4f36a6930eab3198fa6dced", "generation_seconds_batch": 25.653481898945756, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.918426752090454, "target_z": 2.2187499092566423, "ce": 6.181467056274414, "genuineness": 4.507347106933594, "identity": 0.7330971956253052, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/709e911686369fa7385618b442be5b66b96f3cbb261c618b8351a5500589b08c.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "70dbc12361fecbaaa53f482369ebba9e9a87923c9ab98789661943c4b8dc51c1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c7f318fd3ea89132f397f9b73b175501fa7bdd14b9a8449877ccedf07cc4d7a2", "generation_seconds_batch": 22.72691460698843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48104938864707947, "target_z": 0.15917969200380636, "ce": 6.316492557525635, "genuineness": 4.162164688110352, "identity": 0.4289581775665283, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/70dbc12361fecbaaa53f482369ebba9e9a87923c9ab98789661943c4b8dc51c1.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "711aebe95707dfb3487418796b7a0742f0c21346e5d802ee0e35d4e156578c74", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "61e251e6efbf0f744557d5f85804fd28bd1e260ba035fee57d7389035b5c80c5", "generation_seconds_batch": 25.86161808401812, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28646841645240784, "target_z": -0.1196289113376331, "ce": 6.149696350097656, "genuineness": 4.519899368286133, "identity": 0.6618873476982117, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/711aebe95707dfb3487418796b7a0742f0c21346e5d802ee0e35d4e156578c74.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "719a5a9c013e1ee1def27872fa8ba05124c56d82ad1258d943099ef3a6384635", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "d56f9cb97647cfd4a1dcee1d2d411f04f5cf1820bf2529eb8826fc3e4dc655bf", "generation_seconds_batch": 17.347004293929785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5410252809524536, "target_z": 0.24511715330443323, "ce": 6.38003396987915, "genuineness": 4.1998209953308105, "identity": 0.3782224953174591, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/719a5a9c013e1ee1def27872fa8ba05124c56d82ad1258d943099ef3a6384635.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "719bb46124bd2d0106613216c43983e11bc81a23d12530f3c921ad039fca2dd7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "6dee701f45eb34af4012c6d96daac9ef9663a1b0a5ba91d468584f382d8bd96c", "generation_seconds_batch": 24.524625450954773, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2041680812835693, "target_z": 1.195312415928948, "ce": 5.8875885009765625, "genuineness": 4.582659721374512, "identity": 0.7066147923469543, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/719bb46124bd2d0106613216c43983e11bc81a23d12530f3c921ad039fca2dd7.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "72a659bc92cb822ed3ec2424636dd8e2f45cdfca655865ea32ec3d145d20e06a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0453dd5afd9cecaded2885d01854a8cc17d834bcf967f0c1c7c2cdc373078143", "generation_seconds_batch": 24.22604095400311, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32190874218940735, "target_z": -0.06884764732579111, "ce": 5.974957466125488, "genuineness": 4.099404335021973, "identity": 0.23644518852233887, "hypothesis": "Ik 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_Relief/72a659bc92cb822ed3ec2424636dd8e2f45cdfca655865ea32ec3d145d20e06a.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": "72f73de43ef0b68e81769165b234d235596b7a2c024dba6bb0074edbc7641ef5", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "61bba1ec97712eed00e1fb14a66fec218a578394fca8e567e8ba82fedd4f3aeb", "generation_seconds_batch": 23.12738968397025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36893531680107117, "target_z": -0.0014648326572917604, "ce": 6.356205940246582, "genuineness": 4.532451152801514, "identity": 0.4127557873725891, "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_Relief/72f73de43ef0b68e81769165b234d235596b7a2c024dba6bb0074edbc7641ef5.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "747df060b14c218d84ff6e178626c80ad818a0da62e56aa51310e3d46bf60f0a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bc87f22d0a0638a55a52f1dcf6406d2321af5967a6a1524d9388086b7ca98f50", "generation_seconds_batch": 18.49285354395397, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12051232159137726, "target_z": -0.3574218800042293, "ce": 6.054384231567383, "genuineness": 4.344170093536377, "identity": 0.6893269419670105, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/747df060b14c218d84ff6e178626c80ad818a0da62e56aa51310e3d46bf60f0a.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "74ff946c43e55c7bee9ee47182d710283950433632da855b23cfab7d14b553b6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "56fb7a5ad915d7ba85d6e47d9860f4290aae756f1da22f921f4860c097f74911", "generation_seconds_batch": 24.406086859991774, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.53676176071167, "target_z": 1.6718748371957408, "ce": 6.1894097328186035, "genuineness": 4.519899368286133, "identity": 0.5794251561164856, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/74ff946c43e55c7bee9ee47182d710283950433632da855b23cfab7d14b553b6.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "759620be6b931ddd682d4faffcc98d65a466135ca6e3e38050a2a4f0f0a5ca4c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "bcf683559c1adefde879b46743b699a1410d92108307a5b86cd3a2a72a8cfaf9", "generation_seconds_batch": 23.050818285904825, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.863903284072876, "target_z": 2.140625045371679, "ce": 6.308549880981445, "genuineness": 4.532451152801514, "identity": 0.7862727046012878, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/759620be6b931ddd682d4faffcc98d65a466135ca6e3e38050a2a4f0f0a5ca4c.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "75b6401e57edc9aac195f6c88e1c9e23d9c758c824af34eada3b2bf167813b68", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f1346adc8ba956835f770c0e4172d3fcdf990c2339d3cf780828ecbae84b527a", "generation_seconds_batch": 19.03732377209235, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.166001558303833, "target_z": 1.1406248745606526, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.7926099300384521, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/75b6401e57edc9aac195f6c88e1c9e23d9c758c824af34eada3b2bf167813b68.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": "7647dc512d10661485dfd742263a86beede6d0e77f042e1797c65bb5f742b1c9", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bbba7cffacd422fd6bf20198ef89cef21c5bbdcbec7fc8ffedd3d70286850ae8", "generation_seconds_batch": 19.58621364296414, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36859452724456787, "target_z": -0.0019531386782267015, "ce": 6.332377910614014, "genuineness": 4.582659721374512, "identity": 0.5789617300033569, "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_Relief/7647dc512d10661485dfd742263a86beede6d0e77f042e1797c65bb5f742b1c9.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "767139d04d111d1df2e0f3bfc387c658810ac935d0be3e6ef8fc519cf62a8b57", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "771fcf70b8e8272f58ca94bc87d00fe3bbb1c3ab8f2aa8b732696d65ec9e7109", "generation_seconds_batch": 24.638560572988354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5567008256912231, "target_z": 0.2675781199957707, "ce": 6.3641486167907715, "genuineness": 4.2374773025512695, "identity": 0.5234478712081909, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/767139d04d111d1df2e0f3bfc387c658810ac935d0be3e6ef8fc519cf62a8b57.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": "7687e76c2592baf910a3cb2ae7e142db9c5f4f214645e78e0588d89ebea2a0f5", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b33e4d5560aac33f80be57c1b7ed9389079087d96e4e9e98a4a939bab6d2167", "generation_seconds_batch": 20.380593087058514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6534801721572876, "target_z": 0.40625002668922283, "ce": 6.1020402908325195, "genuineness": 4.256305694580078, "identity": 0.42542749643325806, "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_Relief/7687e76c2592baf910a3cb2ae7e142db9c5f4f214645e78e0588d89ebea2a0f5.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "768ce6311cfc488c8fc5888e403863c23c7a13ca04f5a8c36fe2fea284b8660c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "25ce9ddfdb416b13624e44daa2d89aa32e2f9e40926e679dc2eff42bd1ece4ae", "generation_seconds_batch": 20.429997662082314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8225032091140747, "target_z": 0.6484375146790725, "ce": 6.173524379730225, "genuineness": 3.886019229888916, "identity": 0.3617124855518341, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/768ce6311cfc488c8fc5888e403863c23c7a13ca04f5a8c36fe2fea284b8660c.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "7743218027b13f66874dce7b7c89dcf204cc52e71297c68be76abfeae013f577", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "497fa6ba299844b5540143c5ae2212b3e7fce1f7cf9e63656c9e6b465438ee75", "generation_seconds_batch": 23.781606448930688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12869085371494293, "target_z": -0.34570313334038216, "ce": 6.0305562019348145, "genuineness": 4.306513786315918, "identity": 0.7154339551925659, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7743218027b13f66874dce7b7c89dcf204cc52e71297c68be76abfeae013f577.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "6a043cf8a509406a64358d0df676890d9073f4988f3ee2fdf560c384bb605acb", "generation_seconds_batch": 22.91816745197866, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19548222422599792, "target_z": -0.25, "ce": 6.141753673553467, "genuineness": 4.394378662109375, "identity": 0.7879132032394409, "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_Relief/77962898fb95ddc0e92a153772191fe01482e40f98d2245158cb92652e8a93c1.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "7811d57445246bfd79493a4def92f753064e14b5bfba2e8a62b96034a8d91a70", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "019c7b2ca3adc6ef85d7f20cd87cb1639c6fb0a366ff3adf6e61aab88acca6f1", "generation_seconds_batch": 24.371509975986555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8470388054847717, "target_z": 0.683593754670614, "ce": 6.292664527893066, "genuineness": 4.149612903594971, "identity": 0.7072811126708984, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7811d57445246bfd79493a4def92f753064e14b5bfba2e8a62b96034a8d91a70.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "784b8eece325edc836f9c426e795847f0c5393e9eb234cfe98f106ad030d3923", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c07811b9a269453b71b4778ef1b55fbe3c74f012188b8e6ab1f3a681dd0a5185", "generation_seconds_batch": 21.307309853029437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6180398464202881, "target_z": 0.35546876267738087, "ce": 6.173524379730225, "genuineness": 4.7081804275512695, "identity": 0.6247787475585938, "hypothesis": "He encontrado, la cajita estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/784b8eece325edc836f9c426e795847f0c5393e9eb234cfe98f106ad030d3923.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a28564a9c498cd639227286035a8a6fad1ae92188d3856b6d4faf34bfb620872", "generation_seconds_batch": 16.68790042900946, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15595264732837677, "target_z": -0.3066406159923873, "ce": 6.181467056274414, "genuineness": 4.432034492492676, "identity": 0.5717905163764954, "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_Relief/794d3b9296e3c4be7c1e4182a2fa3cf095f7d593990763ce0f19c1f5e499a989.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "7991d4e6b8d946c5937189b2079f9f0279d4c1897ef86b8a40e70afb1cc5de11", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "349e981f0477a7c1de709d42dbdbf6e53d829cb6d3e1567762f08cf4ebe8444b", "generation_seconds_batch": 24.48612298700027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.307762861251831, "target_z": 1.3437499306080207, "ce": 6.221180438995361, "genuineness": 4.362998008728027, "identity": 0.48279890418052673, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7991d4e6b8d946c5937189b2079f9f0279d4c1897ef86b8a40e70afb1cc5de11.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": "799225f3c0b508462dd1116382ac1d57c29e0b46dd51dbcf5a48acdaff10d5bf", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dba7a641dc6822c9929ae654f3887c20e90bbf3a4c2b82a59e1377665d0d195e", "generation_seconds_batch": 21.91696039296221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36825376749038696, "target_z": -0.0024414019964051114, "ce": 6.252951145172119, "genuineness": 4.632867813110352, "identity": 0.710746705532074, "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_Relief/799225f3c0b508462dd1116382ac1d57c29e0b46dd51dbcf5a48acdaff10d5bf.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "799e4f13c3060b1934307f279f32c729a099a3123f865629014f2de67647cbc8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "350a569598280d5d0319e8d29030ab7a14e3e516822adce24b2d424372c184e7", "generation_seconds_batch": 20.8753685640404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6016827821731567, "target_z": 0.3320312693496866, "ce": 6.308549880981445, "genuineness": 4.168440818786621, "identity": 0.34997817873954773, "hypothesis": "The 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_Relief/799e4f13c3060b1934307f279f32c729a099a3123f865629014f2de67647cbc8.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": "7a1b75b6957929ce83bfcd25ffccd2bcb758370fd6840c7c06b8abc020cc33f4", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0957de92294a468bd18739836911aa2b0b04208233cf6f7ff3cae9d3b02f05a8", "generation_seconds_batch": 24.2449606169248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8770267367362976, "target_z": 0.7265624639695492, "ce": 6.316492557525635, "genuineness": 4.6956281661987305, "identity": 0.6529601216316223, "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_Relief/7a1b75b6957929ce83bfcd25ffccd2bcb758370fd6840c7c06b8abc020cc33f4.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "7a4579f8c834eb86494f9b82b3a7636360c3566bfb8db8a22b5ca1d069b30757", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "4eb50fa1b6b7c549c8dda342f7ee3d405d3c2ea7dd88faba7f9985fefee36191", "generation_seconds_batch": 22.39610866107978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.53676176071167, "target_z": 1.6718748371957408, "ce": 6.23706579208374, "genuineness": 4.457139015197754, "identity": 0.3453127443790436, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7a4579f8c834eb86494f9b82b3a7636360c3566bfb8db8a22b5ca1d069b30757.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": "7abe5053f13aa140933c7ab90ca914826a9b4e709b90403ee5243c704be00c73", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "15929f0273184904e75bb9afaf17295f9465480e1893c14857abcb68a926abb9", "generation_seconds_batch": 24.2449606169248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4059052467346191, "target_z": 1.4843748905741865, "ce": 6.348263263702393, "genuineness": 4.68307638168335, "identity": 0.6211620569229126, "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": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7abe5053f13aa140933c7ab90ca914826a9b4e709b90403ee5243c704be00c73.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "7b00047cbf64642fa82cf975dd02bad2ad2b0e2dc3f52d44b377a269d06525ae", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4faf52de6610a04e28150e813e901fa4305803fe95dc553b846f789c9a202959", "generation_seconds_batch": 17.227407495956868, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6185472011566162, "target_z": 1.7890624746452384, "ce": 6.316492557525635, "genuineness": 4.545003414154053, "identity": 0.7021304368972778, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7b00047cbf64642fa82cf975dd02bad2ad2b0e2dc3f52d44b377a269d06525ae.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "7b1c64e0296e2a97d1ebb4a061031c2062f467b7a623b4c5c905bfca4ad90643", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "7f4fa733045caa50b97dabeb46d345e18b80fdab0472cd33518df9cd546bcf5d", "generation_seconds_batch": 23.900935774086975, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5967378616333008, "target_z": 1.7578125974156633, "ce": 6.38797664642334, "genuineness": 3.961331605911255, "identity": 0.4036380648612976, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7b1c64e0296e2a97d1ebb4a061031c2062f467b7a623b4c5c905bfca4ad90643.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "7b8eefaba5182addae653fe701a33804d445c116c86c3b36461825fb17442563", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "25440c5547a78bfead93248893a00e24dbc34a0f9078d5efa24e2c580b720e9c", "generation_seconds_batch": 16.410002109012567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4004528522491455, "target_z": 1.4765623358612796, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.713333249092102, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7b8eefaba5182addae653fe701a33804d445c116c86c3b36461825fb17442563.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": "7bbf9e84c7a3bb4aa397d89e7d538339ef71662e1c07284e2ad37bcb469f12ae", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c0586f90d2a1cfec1986acc9ed9bee8798e51bd60075a325d042184e16fb460f", "generation_seconds_batch": 17.274418262997642, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0078833103179932, "target_z": 0.9140624959966166, "ce": 6.419747352600098, "genuineness": 4.3127899169921875, "identity": 0.31708982586860657, "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_Relief/7bbf9e84c7a3bb4aa397d89e7d538339ef71662e1c07284e2ad37bcb469f12ae.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "7bc89c122020c0149f6c4fcf713441b3dd9780a110fa2aefc10b830921cf61ff", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "349d9d37dd99a6c38be4be79e4ee23f42b302f9d5de0876a0a176f21fe3ffaf9", "generation_seconds_batch": 24.745249446015805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7570749521255493, "target_z": 0.5546875413682953, "ce": 6.41180419921875, "genuineness": 4.293961524963379, "identity": 0.5085082054138184, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7bc89c122020c0149f6c4fcf713441b3dd9780a110fa2aefc10b830921cf61ff.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "7bf978e394f8602d193ac218bdfddf2a607ddd2902f103560f4463c5288c8d8f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "dd664b7938eeb3e8916af1a5326c2c7a0a2ba76b5b2dd88ca42fbc5e812e199e", "generation_seconds_batch": 17.83869888400659, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48036783933639526, "target_z": 0.158203122664693, "ce": 6.395919322967529, "genuineness": 4.281409740447998, "identity": 0.3948298394680023, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7bf978e394f8602d193ac218bdfddf2a607ddd2902f103560f4463c5288c8d8f.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "7c0b1ffa7f3895f019b385b628baa9882258e32fa6da85d3146c2014655c59d2", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "4496078ef24ac7ad74d996c5bb3e6febf03669a8689f0e63b982d0b072116bfa", "generation_seconds_batch": 24.24680736591108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.70391446352005, "target_z": 0.4785156453505324, "ce": 6.443574905395508, "genuineness": 4.356721878051758, "identity": 0.572817862033844, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschalten.", "wer": 0.0625, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7c0b1ffa7f3895f019b385b628baa9882258e32fa6da85d3146c2014655c59d2.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "7c37cb14fbb5159d0f570151d6a12fd8255ffa4b3af4f7423ce3df31bf2f577a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6f33fa9bd5fb392f70e901c39ddf7d00943933b0940e0b5db1854bfb7e16c062", "generation_seconds_batch": 27.602871821960434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.564023733139038, "target_z": 1.7109376107602747, "ce": 6.213237762451172, "genuineness": 3.9173994064331055, "identity": 0.2448064684867859, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7c37cb14fbb5159d0f570151d6a12fd8255ffa4b3af4f7423ce3df31bf2f577a.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "7c80c6582f6b3afa87efbc03ef5cc11cc55b69be12a07020b45ac7b40d158573", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "cbe441cea37884e56c2a060e4cd73558169a0e8d69b49f71c8a72ffc75f7a3fc", "generation_seconds_batch": 15.512249491992407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6153136491775513, "target_z": 0.35156248532092743, "ce": 6.205295085906982, "genuineness": 4.13078498840332, "identity": 0.216323584318161, "hypothesis": "The 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_Relief/7c80c6582f6b3afa87efbc03ef5cc11cc55b69be12a07020b45ac7b40d158573.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "7dab2627a0cadb75fac699414c69129c9178d95117983a8ee5f6436966ca99ee", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "60a9560e9b79cef21fa8f7c3dd8fe41b0cc848b766dc7b965f77e7e692e81f05", "generation_seconds_batch": 25.36891080404166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9806215167045593, "target_z": 0.8749999786486218, "ce": 6.221180438995361, "genuineness": 4.532451152801514, "identity": 0.7129090428352356, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7dab2627a0cadb75fac699414c69129c9178d95117983a8ee5f6436966ca99ee.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "7df8afab9cd3b0800e93e899a13053365c54d7b05c9e5310878530bb48432b79", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "eaf0b3908a7a6b0cb345d6b9f01a33f7dabec3821021ef0a9962d2314c5c78a5", "generation_seconds_batch": 18.516532197012566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2968581914901733, "target_z": 1.3281249919932332, "ce": 6.197352409362793, "genuineness": 4.011539936065674, "identity": 0.20161166787147522, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7df8afab9cd3b0800e93e899a13053365c54d7b05c9e5310878530bb48432b79.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "7e9785073cf29f89ca494b71b955d9b355ba7976566f5de511b65a5c4e0470c6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "965788fc2896aa33e63315f5bd143b954e2ec16587fb535612fad55e80eca281", "generation_seconds_batch": 16.55951545003336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19957149028778076, "target_z": -0.24414062666807643, "ce": 6.125868320465088, "genuineness": 4.325342178344727, "identity": 0.27362295985221863, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7e9785073cf29f89ca494b71b955d9b355ba7976566f5de511b65a5c4e0470c6.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "7ed231094c32966497998a1f7a84a42b8c4d8d5c44d50892ec7f56f9573f2bd8", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4b1c643022d2c499356a184db2e8d59975ce4c2f40b1e84538045d1bfbddf54c", "generation_seconds_batch": 18.192228564992547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4994511008262634, "target_z": 0.1855468933488407, "ce": 6.229123115539551, "genuineness": 4.331617832183838, "identity": 0.7391868829727173, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7ed231094c32966497998a1f7a84a42b8c4d8d5c44d50892ec7f56f9573f2bd8.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "7eed5dfb3b9d77fb56660ebc94461f87ecb3ac8a8b75ffe418a8827bf476e27f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "1523385bd6f0219f0e26996a258c9e6f2a6f3cbf1cb3c484fbdc9d676d122ddd", "generation_seconds_batch": 21.927426425972953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.767979621887207, "target_z": 0.5703124799830829, "ce": 6.109982967376709, "genuineness": 4.545003414154053, "identity": 0.7584803104400635, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7eed5dfb3b9d77fb56660ebc94461f87ecb3ac8a8b75ffe418a8827bf476e27f.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "7f151d2dcf762915fdcdfcd1dfbf76b76cab5682156f428fab2a790794d96cdc", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "3e93260e479dc74a8c35f859078c1a0a6855ce8502056d47f8b29e312e78c061", "generation_seconds_batch": 19.119071808992885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.395000696182251, "target_z": 1.468750122770425, "ce": 6.24500846862793, "genuineness": 4.256305694580078, "identity": 0.4674566984176636, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7f151d2dcf762915fdcdfcd1dfbf76b76cab5682156f428fab2a790794d96cdc.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "efd8b1a19eb9fa5b7fd3167d22ace5a8617f8a6462679254555a05fc637f64a2", "generation_seconds_batch": 16.970057544996962, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4708262085914612, "target_z": 0.14453123732261916, "ce": 6.38797664642334, "genuineness": 4.369274139404297, "identity": 0.31549185514450073, "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_Relief/7f6fce1a6f733719f45a363f28fee4e24b2f07a3396aa07b42392913d7c24239.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "7fab0fab2f9ff5db1acac11c1f89804768f6cc9a1aead0149d8367920792f0cf", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "49cf98db25293e903b346d66296527d2ea561da40cbbe78946658c8b50a6ddaa", "generation_seconds_batch": 18.615392161067575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3747284412384033, "target_z": 0.006835942671036923, "ce": 6.062326908111572, "genuineness": 4.632867813110352, "identity": 0.6985529065132141, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7fab0fab2f9ff5db1acac11c1f89804768f6cc9a1aead0149d8367920792f0cf.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "7fbb6a8b63e7c573529a56f44c773c333dee59b805c1e1fa5471f403c4b55ba9", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c034827bec9e13dfb4002eecaaa99852a1de8e0ae67dddaa5bb1c9f64912cabf", "generation_seconds_batch": 23.835226839990355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8579435348510742, "target_z": 0.6992187786909145, "ce": 6.125868320465088, "genuineness": 4.13078498840332, "identity": 0.604365348815918, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/7fbb6a8b63e7c573529a56f44c773c333dee59b805c1e1fa5471f403c4b55ba9.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "80478051b5f817b4a2670dd7eb0ec1505d187fd1b91f3acdb6eaa55ae2dfc3a8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "ab0de2476408c0bb5a3d5bbb71af332e1f79b0855bc44d2db3ae97b60e37b472", "generation_seconds_batch": 16.928226470947266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4088056683540344, "target_z": 0.055664068004652206, "ce": 6.078212261199951, "genuineness": 4.137060642242432, "identity": 0.5667266845703125, "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_Relief/80478051b5f817b4a2670dd7eb0ec1505d187fd1b91f3acdb6eaa55ae2dfc3a8.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "808a10f5484a5a3c337a806c398c2ef9cc587f70bac6c5237c603197e1a80b88", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "7e1966b4d9ecb5d7f277e9e65cd24346052661a2863336336e5d3b18817340fc", "generation_seconds_batch": 21.13344213308301, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38478121161460876, "target_z": 0.021240222990378387, "ce": 6.022613525390625, "genuineness": 4.519899368286133, "identity": 0.5047962665557861, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/808a10f5484a5a3c337a806c398c2ef9cc587f70bac6c5237c603197e1a80b88.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "d4dde333bd2ed7967667af14bea2998388361ccc20d99fd97ec44a7be7d97b1d", "generation_seconds_batch": 15.993275003042072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32054564356803894, "target_z": -0.07080078600401782, "ce": 6.260893821716309, "genuineness": 4.18099308013916, "identity": 0.6386622190475464, "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_Relief/80c2597a6b8f43b5338a6b37d654868d679f46ded48514b42837ab18fba327ad.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "81230991f5438fe9a70d3da9706784c0e63f57c3dbdadaea804b71f3bdafc6bb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b4cf867e962d84dd722f50fb38e4efbc2872df13c62a2565da0766aa1495f182", "generation_seconds_batch": 24.00299895007629, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2799937427043915, "target_z": -0.12890625600507513, "ce": 6.356205940246582, "genuineness": 4.519899368286133, "identity": 0.32185548543930054, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/81230991f5438fe9a70d3da9706784c0e63f57c3dbdadaea804b71f3bdafc6bb.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "81e84f5718a5f6628d5e3eba4658c565e4eb5596a714b9f7f239f98efbde9002", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "920d5a6b983b442e63ad62f9b6809319a59916c61a636fd8e4964d721d113af8", "generation_seconds_batch": 25.305109695065767, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1223828792572021, "target_z": 1.0781251201015027, "ce": 5.982900142669678, "genuineness": 3.8922953605651855, "identity": 0.5728484392166138, "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_Relief/81e84f5718a5f6628d5e3eba4658c565e4eb5596a714b9f7f239f98efbde9002.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "825c3f3381cafe61739726f942cbe17870a3fccbf23f34bbceae3351a5b9dd84", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "cfa57dfece9e94c984551e4a36140289124f19ff1d7b946f1301408198a7e98e", "generation_seconds_batch": 22.991053901962005, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2750487327575684, "target_z": 1.2968749439526321, "ce": 5.696964263916016, "genuineness": 3.873466968536377, "identity": 0.5448126196861267, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás lista.", "wer": 0.06666666666666667, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/825c3f3381cafe61739726f942cbe17870a3fccbf23f34bbceae3351a5b9dd84.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "826092b118a2c0872d9c7f87f31e9de42cfc00375011bedcf0bf40dd2b1b0d43", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "a934725b7730915fb1a8fd1362767af744c1227f540b43373b1acb63b7ec90fa", "generation_seconds_batch": 25.608992620022036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6221290826797485, "target_z": 0.36132809330654786, "ce": 5.935244083404541, "genuineness": 4.017816066741943, "identity": 0.5304057598114014, "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_Relief/826092b118a2c0872d9c7f87f31e9de42cfc00375011bedcf0bf40dd2b1b0d43.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "8271eedbc413d4a9aa2ce57b8450278a68ac8eaa6b8268dc79de8f701a1b4997", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8b1aa500089f36932c0308f4f93b3ccf5a245a80095654f6139f0487ec918f82", "generation_seconds_batch": 25.255235970951617, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.430615097284317, "target_z": 0.08691407334249678, "ce": 6.38797664642334, "genuineness": 4.319066047668457, "identity": 0.6063203811645508, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8271eedbc413d4a9aa2ce57b8450278a68ac8eaa6b8268dc79de8f701a1b4997.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "8294cc159c083fd0a20a48c8f9568718872d7924c9eba0b88fd2306fb1179efa", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "2b115835dc8a48da46615e94bcea1ccc61becd24bc9dd8067d701846670f7d68", "generation_seconds_batch": 18.550674095051363, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20706848800182343, "target_z": -0.23339842799196436, "ce": 5.935244083404541, "genuineness": 4.394378662109375, "identity": 0.7053298354148865, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8294cc159c083fd0a20a48c8f9568718872d7924c9eba0b88fd2306fb1179efa.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "8299ede3730841cf2ef051f8d15bffcb66137ea392360c197a6057510ce78ead", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e3a13f3c748b01cc838bf8d227aaf293dd7354fe0d55a69c56d62d67289bcbec", "generation_seconds_batch": 25.296027738018893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0378713607788086, "target_z": 0.9570313761065778, "ce": 6.221180438995361, "genuineness": 4.306513786315918, "identity": 0.4109049439430237, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8299ede3730841cf2ef051f8d15bffcb66137ea392360c197a6057510ce78ead.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "82af25ba64a02567ff4a2fb0b56040bd0875dec65067cbf5c7b61fd066f2f748", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "820af5b3b90fb953ffcf9ef2e58643030324acab8a90ccd66700684560943995", "generation_seconds_batch": 18.615392161067575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6071351170539856, "target_z": 0.3398437386570803, "ce": 6.1020402908325195, "genuineness": 4.494794845581055, "identity": 0.7818493843078613, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/82af25ba64a02567ff4a2fb0b56040bd0875dec65067cbf5c7b61fd066f2f748.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "82c085f9fb1b9c79b780ce11924d258acdcb1f40b8c31b7326b343e384e43d08", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9130225ca8ab3b7339b8490a0f46b513da39b15c51c9c00c402a8791a39cf2e4", "generation_seconds_batch": 23.248191789956763, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5049034357070923, "target_z": 0.19335936265623443, "ce": 6.332377910614014, "genuineness": 4.595211505889893, "identity": 0.7900441884994507, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/82c085f9fb1b9c79b780ce11924d258acdcb1f40b8c31b7326b343e384e43d08.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": "8301ecda41941b0dba54ec482fdb7941a2b01de1441a21c4014504f5d60225e9", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1b8a0bd3bf76f46547c503c62df5adee6df74d2566066e8b20e4ae762cc78578", "generation_seconds_batch": 20.380593087058514, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8470388054847717, "target_z": 0.683593754670614, "ce": 6.078212261199951, "genuineness": 4.545003414154053, "identity": 0.714043140411377, "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_Relief/8301ecda41941b0dba54ec482fdb7941a2b01de1441a21c4014504f5d60225e9.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "831cde62d5db461503878c5fccd0310173352cb1e1cbecfd28ffae933912227b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a99544fed3b0edfc56bb25db3f3c5a838b90a0badfd71d220244ef9717ad5548", "generation_seconds_batch": 22.303796604974195, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2377379834651947, "target_z": -0.18945312800253758, "ce": 5.879645347595215, "genuineness": 4.281409740447998, "identity": 0.18956705927848816, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/831cde62d5db461503878c5fccd0310173352cb1e1cbecfd28ffae933912227b.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "8320c79bf2e8b94a95b1d5ef27b5a32973ac90f18da38ec76e8b7e64ba74fa33", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "578083287bcb3b3f3f0ec795f83e721c63812adfbc21a39273675007d971263a", "generation_seconds_batch": 27.33497404505033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.749403715133667, "target_z": 1.9765624212667927, "ce": 6.117925643920898, "genuineness": 4.494794845581055, "identity": 0.6049665212631226, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8320c79bf2e8b94a95b1d5ef27b5a32973ac90f18da38ec76e8b7e64ba74fa33.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "8323a51a9ed90a5a9d1adbf2d47d34b5e7e3dd8d27913a2a13065d4f051a1fb5", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ca35dd6e6b9660b482e9df0f5e76bacc38ed5a4cd3ee5ebe4a92878b1f52498", "generation_seconds_batch": 24.741545588010922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6316707134246826, "target_z": 0.3749999786486217, "ce": 6.078212261199951, "genuineness": 4.469690799713135, "identity": 0.1043112576007843, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8323a51a9ed90a5a9d1adbf2d47d34b5e7e3dd8d27913a2a13065d4f051a1fb5.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "83b32b6600c5d03bf31871ecbf18f8d9f7c5751877a89d0e697a0232f52e78d7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "021336bf9be97f8a1577589e42d4584aed7e5a787a45bb9a5bc5dd83219bb2c2", "generation_seconds_batch": 21.98693248501513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6630218029022217, "target_z": 0.4199219120312967, "ce": 5.7128496170043945, "genuineness": 3.616149425506592, "identity": 0.39712345600128174, "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_Relief/83b32b6600c5d03bf31871ecbf18f8d9f7c5751877a89d0e697a0232f52e78d7.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "83dac0cce1f2a15205b38a7f85916960d4d367eaf8b73a0f67a54b334f25c73c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "b27c3dd464d538ee12ff0cd0439d1fd59fc56fbfd9d3e293fe539bfb16b76c84", "generation_seconds_batch": 23.088593100081198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5040476322174072, "target_z": 1.6249998505403522, "ce": 5.95112943649292, "genuineness": 4.231201171875, "identity": 0.577325165271759, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "wer": 0.058823529411764705, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/83dac0cce1f2a15205b38a7f85916960d4d367eaf8b73a0f67a54b334f25c73c.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "83e10069b17ceac67ed399fdf3dc7c472e2846b3fac322afdb8d41f431e894d1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71de6fa3721785d8e5b3f730f8142deb7b1c2227962b4f878b4b1920dda2dcc6", "generation_seconds_batch": 25.36891080404166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43606746196746826, "target_z": 0.09472658535264705, "ce": 6.046441555023193, "genuineness": 4.18726921081543, "identity": 0.6322610378265381, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/83e10069b17ceac67ed399fdf3dc7c472e2846b3fac322afdb8d41f431e894d1.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "83f384cdc0c873342edfff9bcb76a6785ff9f402f7bfae11a88fc82002877d41", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e3a148b07be852b80d4d05d904295383a69c2d7d97cdace8c53a5431445897d2", "generation_seconds_batch": 24.43107263208367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.315434068441391, "target_z": -0.07812499199323315, "ce": 6.086154937744141, "genuineness": 4.557555198669434, "identity": 0.68336021900177, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/83f384cdc0c873342edfff9bcb76a6785ff9f402f7bfae11a88fc82002877d41.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "84daa29c1e04c1d424c4a4ba0a546dc6b199b666120b7bf303aa1f96c1a9fcc6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5ce21fb572e7053ec4645bbeb677e1f796e9497f35cb0996f7c7ade5a4a8a4d8", "generation_seconds_batch": 19.137854815926403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7270869612693787, "target_z": 0.5117187466638471, "ce": 6.38797664642334, "genuineness": 4.017816066741943, "identity": 0.5047042369842529, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/84daa29c1e04c1d424c4a4ba0a546dc6b199b666120b7bf303aa1f96c1a9fcc6.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": "84e159e1f242142e494f7ab407d7b66ac9a4bea54e0091916c73daafff3e6190", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6909f069dd7363a8f95ca3480cc8b9ee4ff31d06d97a1ae341b44aad3d4a6463", "generation_seconds_batch": 18.683470105053857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5935042500495911, "target_z": 0.32031252268583943, "ce": 6.062326908111572, "genuineness": 4.6956281661987305, "identity": 0.5961569547653198, "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_Relief/84e159e1f242142e494f7ab407d7b66ac9a4bea54e0091916c73daafff3e6190.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "84e8814c6f357e6932b5aff45009af549a5719a210bbf794a2a38733e45108bf", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d8153c7910c86c5587d182add8e40e58f84e48ac4d70d0197edf6b1a86a7db79", "generation_seconds_batch": 25.63570612797048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29873621463775635, "target_z": -0.10205079134186239, "ce": 6.284721851348877, "genuineness": 4.406930446624756, "identity": 0.7112900614738464, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/84e8814c6f357e6932b5aff45009af549a5719a210bbf794a2a38733e45108bf.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "84ed601d6b01e48347c91e374de3d87b817923797177b24ef810a6e7299763d3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "480b27ed4f07e734114acd96c4e6b8c5b9839ac1c205e7d2a685392025e77f90", "generation_seconds_batch": 16.304784015985206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7379916906356812, "target_z": 0.5273437706841477, "ce": 6.173524379730225, "genuineness": 4.293961524963379, "identity": 0.5602518320083618, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/84ed601d6b01e48347c91e374de3d87b817923797177b24ef810a6e7299763d3.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": "854140ab526d34ebe4861bffee695a2f93ab663ec5dcc8ef9898447bb285ac50", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c34d9786438d7e0e177f596ee56af84269e519fed3303a408d718ac35093aa28", "generation_seconds_batch": 19.82387769804336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5253497958183289, "target_z": 0.22265627201860883, "ce": 6.141753673553467, "genuineness": 4.545003414154053, "identity": 0.7215757369995117, "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_Relief/854140ab526d34ebe4861bffee695a2f93ab663ec5dcc8ef9898447bb285ac50.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "855db404c1ff82b6f119a982fa0305566a9a172c7760071f2a2360b78b215e71", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "6e73d33cc6b8e2f044b514cfed1b36a456ce4222b5159555b2fc018a627eab98", "generation_seconds_batch": 21.783989766030572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.231429934501648, "target_z": 1.234375018682456, "ce": 6.173524379730225, "genuineness": 4.293961524963379, "identity": 0.40232300758361816, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/855db404c1ff82b6f119a982fa0305566a9a172c7760071f2a2360b78b215e71.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "86035ceaf81fe73486e1bb9c269113cc51df13b037ce565ac13f5e35c11e7c83", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f50a5e37b01b44d663bd25f2c0cc7b377f26d3918bc918f21eb4b448ec4ba1ee", "generation_seconds_batch": 16.598384245997295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2568212151527405, "target_z": -0.1621094000211464, "ce": 6.149696350097656, "genuineness": 4.457139015197754, "identity": 0.6142042875289917, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/86035ceaf81fe73486e1bb9c269113cc51df13b037ce565ac13f5e35c11e7c83.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "8658b435104ef50ee00af255789451e246f4ba4c0803cb8515f3cbb68b3cd1ed", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "adbfa2ad478e09c89299a02e9bedda1a230da97810ebaf3bdeaa5bac41a83dd8", "generation_seconds_batch": 24.79009462101385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20161612331867218, "target_z": -0.24121094000211465, "ce": 6.062326908111572, "genuineness": 4.268857479095459, "identity": 0.7575092911720276, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8658b435104ef50ee00af255789451e246f4ba4c0803cb8515f3cbb68b3cd1ed.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "86669d0cde83f1cda43593b6e28f1a7ab6314f5c1762c61c582c10d41efbc084", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "69f1cfb62044c9cc1e9db5e1f672a931e43bea714431d98333904f9f544cee60", "generation_seconds_batch": 26.263341599027626, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5749282836914062, "target_z": 1.726562378564036, "ce": 6.141753673553467, "genuineness": 4.13078498840332, "identity": 0.3126737177371979, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/86669d0cde83f1cda43593b6e28f1a7ab6314f5c1762c61c582c10d41efbc084.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "87b111c672cd2e8cce6380bbd1538e49590f13057f8e24940c6139fd83cee116", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "a12021cb360ba9a878923684d3e629829cf1911d415d1caec48dca986fb1d4f3", "generation_seconds_batch": 24.321183460997418, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2859535217285156, "target_z": 1.3125000533784457, "ce": 6.133810997009277, "genuineness": 4.331617832183838, "identity": 0.7434833645820618, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/87b111c672cd2e8cce6380bbd1538e49590f13057f8e24940c6139fd83cee116.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "87f6bcb14597a5a4191613478d52435ab1ab3fb2b047adc53bc183b06327b633", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dfdbe21fc54382bed2beb2274ca16644b5962e370d676c09f8ba9fca23ca7a5c", "generation_seconds_batch": 24.75546178605873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.607642412185669, "target_z": 1.7734373652194246, "ce": 6.260893821716309, "genuineness": 4.2751336097717285, "identity": 0.7301257252693176, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/87f6bcb14597a5a4191613478d52435ab1ab3fb2b047adc53bc183b06327b633.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "88501d8982c4bc9e66758acea0377f3f0cf7af68b031b1d5b5a91f3f61830583", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e25866b5d2cb4bc1936093b03a7a0cefd55a6c4b837b1ca05525e01c0b207a31", "generation_seconds_batch": 22.187126793083735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37643229961395264, "target_z": 0.009277344667442036, "ce": 6.292664527893066, "genuineness": 4.457139015197754, "identity": 0.6528854370117188, "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_Relief/88501d8982c4bc9e66758acea0377f3f0cf7af68b031b1d5b5a91f3f61830583.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "890aabde97badba9bcff1efee5085124da52b1f4ef53ae1e76dc300fd8b0a8fb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "38e483e3d105ebb5f19d00415fd4058ccf6dcbc79bab263cf5f97a343e795bbb", "generation_seconds_batch": 24.704380425973795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7543487548828125, "target_z": 0.550781264011842, "ce": 6.252951145172119, "genuineness": 4.118232727050781, "identity": 0.16626721620559692, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/890aabde97badba9bcff1efee5085124da52b1f4ef53ae1e76dc300fd8b0a8fb.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "8936f443e0c6d1d6dc14c679ada53db1b1add90a23e1c741ee83633ac27a1ecc", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dad18875848f8f6bc56f744d6edd85c7ab9987fddeec585b5ab4d95096d17af9", "generation_seconds_batch": 24.832552770036273, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.25409504771232605, "target_z": -0.1660156346748433, "ce": 6.086154937744141, "genuineness": 4.319066047668457, "identity": 0.31995102763175964, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8936f443e0c6d1d6dc14c679ada53db1b1add90a23e1c741ee83633ac27a1ecc.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "89743fe70c4f653a9bacba42f79d6c7eb7635735e31dfa302f2ed669393e0305", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "900a6cdb490ba5ffc08d530232d46b62cc31cf261e537d3a7e55b93b05a6f2df", "generation_seconds_batch": 24.75534830603283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7275943756103516, "target_z": 1.9453125440372177, "ce": 6.078212261199951, "genuineness": 4.281409740447998, "identity": 0.5414210557937622, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hace.", "wer": 0.11764705882352941, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/89743fe70c4f653a9bacba42f79d6c7eb7635735e31dfa302f2ed669393e0305.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": "89c9523f2ce2df530e452643cd86162f25fc886d0961d40af4e58bf3d0704942", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dc013446bd4ac1a9bec0084034998e59f14973b8b7515a3eb37ed7400ee98d8c", "generation_seconds_batch": 17.869360032025725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6316707134246826, "target_z": 0.3749999786486217, "ce": 6.205295085906982, "genuineness": 4.645420074462891, "identity": 0.7395750284194946, "hypothesis": "Mes 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": 0.041666666666666664, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/89c9523f2ce2df530e452643cd86162f25fc886d0961d40af4e58bf3d0704942.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "89d77576be7f0228b83400674b33ccf735ef3923fe91f65a7825557a60999b75", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "65e64a06e75efd5b15c9ec6d1f04f7dfe764b61499be1791d5431919f5b5d234", "generation_seconds_batch": 17.10378360399045, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31270790100097656, "target_z": -0.08203122664693002, "ce": 6.2767791748046875, "genuineness": 4.193545341491699, "identity": 0.5343032479286194, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/89d77576be7f0228b83400674b33ccf735ef3923fe91f65a7825557a60999b75.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "89d9ce20b8d4b1211510c657dcbbdb3231010a08b052dfe70eb793f7f19c881a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "12dde8feb323459b46dc53d525753305c4286b856838d71f992b76ee86fb350d", "generation_seconds_batch": 17.78302770096343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13823248445987701, "target_z": -0.3320312479983083, "ce": 6.23706579208374, "genuineness": 4.356721878051758, "identity": 0.7636849880218506, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/89d9ce20b8d4b1211510c657dcbbdb3231010a08b052dfe70eb793f7f19c881a.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": "8a180f1428dca499f90275dd3649e856f1b0992d80423ab3c85924d9b8493a94", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "b444d3cb67a23b81bd488bc49d669edb58a14855afd4bb7d28a2fc932440744f", "generation_seconds_batch": 21.590356310014613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3404769897460938, "target_z": 1.3906249172634093, "ce": 6.348263263702393, "genuineness": 4.632867813110352, "identity": 0.711632490158081, "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_Relief/8a180f1428dca499f90275dd3649e856f1b0992d80423ab3c85924d9b8493a94.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "8ae3ed79e40e537e801f37168cd5f688a29f3a782e5e9c05793aa4fd8f8dd5ac", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6ad55ea46b9d9eec1badd31caf34a8a3ffca1e4014548bc1b283a02a07558876", "generation_seconds_batch": 15.49601408408489, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3452516496181488, "target_z": -0.03540037165063064, "ce": 6.213237762451172, "genuineness": 4.432034492492676, "identity": 0.6239299774169922, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8ae3ed79e40e537e801f37168cd5f688a29f3a782e5e9c05793aa4fd8f8dd5ac.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "8bbbde207ec8abf2364e93e426d1ac88138d6395ebc498b2f132038d6461f436", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "bd723d6c350f9c6d1d8c0403a62d40edbfca1c7a2d1e0e67a475dbe6ca6dfc74", "generation_seconds_batch": 25.04595324397087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2588658630847931, "target_z": -0.15917969200380636, "ce": 6.205295085906982, "genuineness": 4.3881025314331055, "identity": 0.4853481650352478, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8bbbde207ec8abf2364e93e426d1ac88138d6395ebc498b2f132038d6461f436.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "8bfe6e45bcdda27f6acd711195dfb1a26025420f333c019a3751b6befe6ac190", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a01c8e967b983e50a773e033793afc70ac20c599aed06997490803801a95cf59", "generation_seconds_batch": 18.09948416100815, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6294519901275635, "target_z": 1.804687584071052, "ce": 6.2767791748046875, "genuineness": 4.287685871124268, "identity": 0.40327203273773193, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8bfe6e45bcdda27f6acd711195dfb1a26025420f333c019a3751b6befe6ac190.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "8c68f5d13c2eb9827ccb43863bf43626872a7b2b8559b9416baa91b8c9fce5b4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "0e58d272d258313b44d7d59fd58e7f686d50cd46696506351d0828f53dc35966", "generation_seconds_batch": 24.591780386981554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1278351545333862, "target_z": 1.0859375040033834, "ce": 6.197352409362793, "genuineness": 4.243753433227539, "identity": 0.3773319721221924, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8c68f5d13c2eb9827ccb43863bf43626872a7b2b8559b9416baa91b8c9fce5b4.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": "8ca54869061e07ef5c655f1e42735e8a453bf58d05982491e50ce3420d0c404f", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "830b1e8efd8e4aca43d6888e2d572b58e3dd68ea0fd21179e9f4d0a323b18027", "generation_seconds_batch": 20.202549600042403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.517852783203125, "target_z": 0.2119140519911185, "ce": 6.41180419921875, "genuineness": 4.400654315948486, "identity": 0.5435580611228943, "hypothesis": "Las llaves están en la mesa de la cocina. Mienen 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_Relief/8ca54869061e07ef5c655f1e42735e8a453bf58d05982491e50ce3420d0c404f.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": "8cee108078fe4a28fa707f67e070051e1baba3142c8ddaa7bca4e7d40250e45a", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "792283d418ae88de66d6ac98dcd62ce2a6386e9b0be426dfb25b238739d3bf35", "generation_seconds_batch": 17.105603880016133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5771471858024597, "target_z": 0.29687502935814514, "ce": 6.157639026641846, "genuineness": 4.469690799713135, "identity": 0.5593865513801575, "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_Relief/8cee108078fe4a28fa707f67e070051e1baba3142c8ddaa7bca4e7d40250e45a.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "8d0cf7d325425fc1c6303a00f2d104ddcbd945e9a7575c0573172b69893c2c3c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0948c8cfba8e2184a5f236be9ef7bc884d42cae0934f7408a6de164873b46361", "generation_seconds_batch": 22.094615316949785, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28578686714172363, "target_z": -0.12060548067674645, "ce": 6.205295085906982, "genuineness": 4.306513786315918, "identity": 0.7168561816215515, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8d0cf7d325425fc1c6303a00f2d104ddcbd945e9a7575c0573172b69893c2c3c.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": "8d6fee3e99a69c579fa3aa524c3fcf264916df0e94312a5c2381c2fb9ac52c47", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "42f8fd8de25464890fc175a49623269532892c173897da48180eaac925c0d5bf", "generation_seconds_batch": 24.41706253204029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39074474573135376, "target_z": 0.029785172680552807, "ce": 6.157639026641846, "genuineness": 4.369274139404297, "identity": 0.2672029733657837, "hypothesis": "But the keys are on the kitchen table. I checked the drawer, then looked beside the window. Take them with you when you leave.", "wer": 0.043478260869565216, "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_Relief/8d6fee3e99a69c579fa3aa524c3fcf264916df0e94312a5c2381c2fb9ac52c47.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "8d79892308a614e1278a158d4032f438e809c7b3fff7fbdf7ccdaaf5e43bcbc3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "628880a20f137cffce48fc78b5b85aca74ee78f47ad949130e13d91f4460118f", "generation_seconds_batch": 23.202106893993914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30964094400405884, "target_z": -0.08642576732156183, "ce": 6.0146708488464355, "genuineness": 4.281409740447998, "identity": 0.2807571291923523, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8d79892308a614e1278a158d4032f438e809c7b3fff7fbdf7ccdaaf5e43bcbc3.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "8db3bd60fbd3ec32e79268dfaaffdfab2f828bbeb9a0b82a662c680086ca970c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3d808f9cdc1636059745324f05d1971111c484facb19e33e9dca4b47261b2c01", "generation_seconds_batch": 22.839216521009803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8966174125671387, "target_z": 2.187500032027067, "ce": 6.229123115539551, "genuineness": 4.268857479095459, "identity": 0.7908558249473572, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre.", "wer": 0.3684210526315789, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/8db3bd60fbd3ec32e79268dfaaffdfab2f828bbeb9a0b82a662c680086ca970c.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": "8dd08d343f6426165f9531996c6bca85e2a62e6bedea851a3fb4dd9bc63765ad", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ddf63f3fe7c64f4924f478cf32522868ce155541eabc0c92b48b0d580a183e44", "generation_seconds_batch": 17.522399508045055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5457960963249207, "target_z": 0.25195309597547016, "ce": 6.324435234069824, "genuineness": 3.8797430992126465, "identity": 0.13760817050933838, "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_Relief/8dd08d343f6426165f9531996c6bca85e2a62e6bedea851a3fb4dd9bc63765ad.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": "8f399d32c0a7b2638521867202a542e5a37c28541b78d160de50087c4c3849b3", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "900e58f19a336fe96471f4f148733b7f88f0359c36bbab9082977cea62436842", "generation_seconds_batch": 16.13522686099168, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6234921813011169, "target_z": 0.3632812319847746, "ce": 6.348263263702393, "genuineness": 4.118232727050781, "identity": 0.43268537521362305, "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_Relief/8f399d32c0a7b2638521867202a542e5a37c28541b78d160de50087c4c3849b3.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "903288fd5e6f24f24dd576477c52752322539a5106a2b15e2b40caa21502f2bf", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "1640dfd0d7ad93f20294ffb3d1c9eed30331e078e5bd707b128280a4b12c526d", "generation_seconds_batch": 18.91695726895705, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2844237685203552, "target_z": -0.12255861935497316, "ce": 6.181467056274414, "genuineness": 4.494794845581055, "identity": 0.590501606464386, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/903288fd5e6f24f24dd576477c52752322539a5106a2b15e2b40caa21502f2bf.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "90525ebe896ba98f8f611853a07bbfaf6b349e8b02a66c08c80113c0869891cb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8d0ec97c9f6fd94f247cd7a08adeacb76877d27b16a713219c4485e10cbec6d3", "generation_seconds_batch": 21.373594750999473, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4612845778465271, "target_z": 0.1308593519805453, "ce": 6.292664527893066, "genuineness": 4.20609712600708, "identity": 0.5205544233322144, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/90525ebe896ba98f8f611853a07bbfaf6b349e8b02a66c08c80113c0869891cb.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "90ab1ebff9c460c08037d7bc712b4431afd56c606a20ee9a6466aa6ddfec8b48", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "18e0e4a898f339479464b41b7cb4158a3900ecdd2fa6f99b5be227334d442cbb", "generation_seconds_batch": 25.265932149020955, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.694372832775116, "target_z": 0.46484376000845856, "ce": 6.197352409362793, "genuineness": 4.469690799713135, "identity": 0.6654020547866821, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/90ab1ebff9c460c08037d7bc712b4431afd56c606a20ee9a6466aa6ddfec8b48.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "9113bf964230ce268764ae03b490067c856a71424c57cc236eebb892a7ed4c5e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "26691722a379f968da4efa79ea3e075fe099b637ccac110cfc19d1a28ccd31bc", "generation_seconds_batch": 24.039762314991094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4604289531707764, "target_z": 1.562500096081202, "ce": 6.070269584655762, "genuineness": 4.13078498840332, "identity": 0.728880763053894, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/9113bf964230ce268764ae03b490067c856a71424c57cc236eebb892a7ed4c5e.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "911f420bbdf7694f018ca61e6f059f045ad65c1df73aea457c272964947a63e3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9d87bfcf4ecc0ba8e38cbfa0e135aca87876e733280592e90e738562a19b9466", "generation_seconds_batch": 24.00299895007629, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43334126472473145, "target_z": 0.09082030799619364, "ce": 6.459460258483887, "genuineness": 4.545003414154053, "identity": 0.6401898860931396, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/911f420bbdf7694f018ca61e6f059f045ad65c1df73aea457c272964947a63e3.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "917c63021d9ca14b968b76abadf8b4cd9f9f3bf4ba947b4bcfdf2f11458c56b5", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "75f3a8fc92228e73684c2923a6d277893774922fee79f0683174c8849f4d0fc2", "generation_seconds_batch": 18.16742026398424, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4387936294078827, "target_z": 0.09863282000634392, "ce": 6.340320587158203, "genuineness": 4.457139015197754, "identity": 0.22645914554595947, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/917c63021d9ca14b968b76abadf8b4cd9f9f3bf4ba947b4bcfdf2f11458c56b5.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "91ccb608641e224e05c786b96c8c2802222e32863b41f9c0a52a70ee28d147fa", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e75c7b7aebfe80c931641a82902d8ba99a45bea2d94f26be4d10c632231cf689", "generation_seconds_batch": 21.045565478969365, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1600419133901596, "target_z": -0.30078124266046374, "ce": 6.173524379730225, "genuineness": 4.469690799713135, "identity": 0.3961813747882843, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/91ccb608641e224e05c786b96c8c2802222e32863b41f9c0a52a70ee28d147fa.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "91d94cb1ac238d255250f71a043dbded401342fd28f6af327bb58dabff560963", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8426c92e2f5ddab31e7fe7df6a849e737edcb1d99a893f12848fee914811e171", "generation_seconds_batch": 24.40528574900236, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6166767477989197, "target_z": 0.35351562399915415, "ce": 6.4912309646606445, "genuineness": 4.300237655639648, "identity": 0.4801214933395386, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/91d94cb1ac238d255250f71a043dbded401342fd28f6af327bb58dabff560963.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": "91e4b2734bf38e144013767975f12e1ab576150c149cec045fa1327c91f56a7d", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Take them with you when you leave.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The keys are on the kitchen table.\n(Natural clear speech.) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Natural clear speech.) [3.2 seconds duration] Take them with you when you leave.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4ab82a7e3f9fc1dc026874c59394ae3bf973ef9d116c7efed4e3a86fcabbe1ce", "generation_seconds_batch": 17.417378176003695, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8688482046127319, "target_z": 0.7148437173057021, "ce": 6.372091293334961, "genuineness": 4.243753433227539, "identity": 0.4675264358520508, "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_Relief/91e4b2734bf38e144013767975f12e1ab576150c149cec045fa1327c91f56a7d.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "91ed58e48f112202ce952ba8208f7d58a1a928b54e69893c3eb68da52892d335", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "982629ca0b8f3c4943cb285de0ba5af5f59db27bfbceff82399377bc89c98a03", "generation_seconds_batch": 21.886650168919004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6371231079101562, "target_z": 0.38281253336152854, "ce": 6.443574905395508, "genuineness": 4.042920112609863, "identity": 0.44618088006973267, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/91ed58e48f112202ce952ba8208f7d58a1a928b54e69893c3eb68da52892d335.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": "91f61fc32d7c9be8744199f8a54cca467d0196efd30d045dc103017ea31e01a2", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e9e0729f73e547685d5186a605e8668f37dd5302cd9ff5813f0ebb21d74e2d6b", "generation_seconds_batch": 17.468088551075198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38835933804512024, "target_z": 0.026367201345034345, "ce": 6.483288764953613, "genuineness": 4.457139015197754, "identity": 0.37727630138397217, "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_Relief/91f61fc32d7c9be8744199f8a54cca467d0196efd30d045dc103017ea31e01a2.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "92170e532758daaf23caad6d224186accea06ea20455480e5d0e16fb6c43e3bb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9736b48c74b827194c4dadf6075e3f54bde7232761277c3d721aba7ddaa02737", "generation_seconds_batch": 24.398639764986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4599215090274811, "target_z": 0.12890625600507513, "ce": 6.260893821716309, "genuineness": 4.457139015197754, "identity": 0.6177545785903931, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/92170e532758daaf23caad6d224186accea06ea20455480e5d0e16fb6c43e3bb.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "935653a5f5810ca63be8fe19ad136e90f8ea806ea7e4b6aea32087226f05a309", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "98b2a6a2ecc71257eee6f08e396b4592311b7d3c6bd5647126727c033d8fb932", "generation_seconds_batch": 24.591780386981554, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7875702381134033, "target_z": 2.031249962635088, "ce": 6.141753673553467, "genuineness": 4.13078498840332, "identity": 0.30294346809387207, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/935653a5f5810ca63be8fe19ad136e90f8ea806ea7e4b6aea32087226f05a309.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "9374878e521ddc60adc563ea09972128c1869236f777dea3dcdf496c358f086f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "316d9b297900ce9a9a684932590f1700a07eb3a6abfe2e40c228bbb823923710", "generation_seconds_batch": 22.61509523296263, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1441922187805176, "target_z": 1.1093749973310778, "ce": 6.213237762451172, "genuineness": 4.325342178344727, "identity": 0.584630012512207, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/9374878e521ddc60adc563ea09972128c1869236f777dea3dcdf496c358f086f.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "93d328b3d72e87a959c8cadd3b3d100612ddd737217d7d3f5b71b96fa2f02ed8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8ea50470f992a65bb7050283e343915ce13fd762ca8b926de54d5d0624153883", "generation_seconds_batch": 24.314618165954016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.37864351272583, "target_z": 1.4453124586317045, "ce": 6.173524379730225, "genuineness": 4.268857479095459, "identity": 0.6751529574394226, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/93d328b3d72e87a959c8cadd3b3d100612ddd737217d7d3f5b71b96fa2f02ed8.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "94b7bd4b53ed72697c9e6483e66c99f46df728e2042285ec3be0be2b34ad8b1d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "b11ee0ccec9bc72e6f4b9070ffacc15eb1c6e475382501b14430e64a1dc8d53e", "generation_seconds_batch": 24.627454808098264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4295927882194519, "target_z": 0.08544924068520501, "ce": 6.41180419921875, "genuineness": 4.099404335021973, "identity": 0.5015931129455566, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/94b7bd4b53ed72697c9e6483e66c99f46df728e2042285ec3be0be2b34ad8b1d.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "94dbcabcd5ea92a79b3fa77a4dc11f9bba22a66a3adbc1f9534ea9ad8c2ad2ca", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "08f550080ecbc1f83e00dbbc211f486244198cd3c5f102cd2a323dd7e6841545", "generation_seconds_batch": 25.869001772953197, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6185472011566162, "target_z": 1.7890624746452384, "ce": 6.117925643920898, "genuineness": 4.20609712600708, "identity": 0.5539864897727966, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what it contiens.", "wer": 0.3157894736842105, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/94dbcabcd5ea92a79b3fa77a4dc11f9bba22a66a3adbc1f9534ea9ad8c2ad2ca.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": "94e754839114f1ca19a5eaa9988355eb48aa9e8bc1ce64f7d2c055ff28d7c0f3", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3e28c3e237ab2135f725db74defc6041058d84cda3c061d1a53b87b3a5476491", "generation_seconds_batch": 18.647716079023667, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5703316926956177, "target_z": 0.2871093359670116, "ce": 6.316492557525635, "genuineness": 4.406930446624756, "identity": 0.7458216547966003, "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_Relief/94e754839114f1ca19a5eaa9988355eb48aa9e8bc1ce64f7d2c055ff28d7c0f3.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": "95075c35df1434db6d9730c80169e968426d944c3a13920a42be35ac0ab8ad48", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "24bb2fa3ab2b72b0a08051af4c00894ecbd1adb18b4ed84cdfa1d21732ed03c0", "generation_seconds_batch": 18.62828514992725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9402363300323486, "target_z": 2.2500001281082698, "ce": 6.2767791748046875, "genuineness": 4.406930446624756, "identity": 0.5838203430175781, "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_Relief/95075c35df1434db6d9730c80169e968426d944c3a13920a42be35ac0ab8ad48.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "9507b09acff6430717f7156c17074c18355b29cfb3282666cd1977372e10ce54", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "772b28d88828d807a4bb679bc10b9d281bd30354f69981f60ff63aa7e5057bc4", "generation_seconds_batch": 23.428426111931913, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21115775406360626, "target_z": -0.2275390546600408, "ce": 6.133810997009277, "genuineness": 4.243753433227539, "identity": 0.7169445753097534, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/9507b09acff6430717f7156c17074c18355b29cfb3282666cd1977372e10ce54.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "9587dabc742aa5210a6451de6a8a6f3950cd3a77967569d2c28103103b96500c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "f8deb60202bbad6d0cba73c4b678223f06cc81cf1fa3d09408d673cc98791757", "generation_seconds_batch": 22.335830855066888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3702983856201172, "target_z": 0.00048826331817840974, "ce": 6.348263263702393, "genuineness": 4.507347106933594, "identity": 0.4632907211780548, "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_Relief/9587dabc742aa5210a6451de6a8a6f3950cd3a77967569d2c28103103b96500c.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": "9597bdd0251db6ebd216c41777cde9fe67f181609df9c1e709279ab93094bd28", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "0528705062478329f89dd424a85bd5569a60a53e813b73e1100ee654879fe7a7", "generation_seconds_batch": 17.869360032025725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8906576633453369, "target_z": 0.7460937653463031, "ce": 6.117925643920898, "genuineness": 4.494794845581055, "identity": 0.6777966022491455, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends-les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/9597bdd0251db6ebd216c41777cde9fe67f181609df9c1e709279ab93094bd28.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "95a08da49e3ec366fcd72de4dd5e2c729aa5573d3ff1c75b074285c9eee278c5", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "03948c25c00f84256a69e4617b815fa41e5ef671606da9bc50c02e36660c05d6", "generation_seconds_batch": 24.638560572988354, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5825995206832886, "target_z": 0.30468749866553885, "ce": 6.23706579208374, "genuineness": 4.030367851257324, "identity": 0.4199925661087036, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/95a08da49e3ec366fcd72de4dd5e2c729aa5573d3ff1c75b074285c9eee278c5.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "962934cc495c0c7af1a7b55ebb97c576b05409e319f697baf049ed5b27f13d22", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "f4c91232b8204d7685a2b606010aceff5d825e069a246c452a68a319547042bd", "generation_seconds_batch": 25.586160354083404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6239995956420898, "target_z": 1.796875029358145, "ce": 5.748591423034668, "genuineness": 4.105680465698242, "identity": 0.6449131965637207, "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_Relief/962934cc495c0c7af1a7b55ebb97c576b05409e319f697baf049ed5b27f13d22.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": "962edcf197589180a58691a41da45fa2b9d076090fdd2611737ef8351677d85d", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4055e4badff4ad093c94156914ce4aab22c2a4e44ae2107cab40b5de47be573c", "generation_seconds_batch": 26.119101432967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9402363300323486, "target_z": 2.2500001281082698, "ce": 6.332377910614014, "genuineness": 4.557555198669434, "identity": 0.7285467386245728, "hypothesis": "Ton message is arrived after my départ. Je l'ai relu, puis j'ai rangé mon téléphone. Dis-moi quand nous pouvons parler.", "wer": 0.23809523809523808, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/962edcf197589180a58691a41da45fa2b9d076090fdd2611737ef8351677d85d.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "963e9a9ca42732b587a70cde351b206f6fe7e5340d78f6146a622f845a45cba6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "6d471b6bd73f4f6ff2a38d9221e226c74c0c11639b132134dfb97bf6f35a8d45", "generation_seconds_batch": 16.234699595952407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6712002754211426, "target_z": 0.43164057328963074, "ce": 6.157639026641846, "genuineness": 4.281409740447998, "identity": 0.7843743562698364, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/963e9a9ca42732b587a70cde351b206f6fe7e5340d78f6146a622f845a45cba6.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": "9809b7cd11bff87a89d391f6ea2d5425e24a104453819d054114953f65e78784", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5b3604aaec194e0f33b484e2027f70b8bd19d9b9065fe153a8ddc3131c230426", "generation_seconds_batch": 17.105603880016133, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.449524164199829, "target_z": 1.5468749866553886, "ce": 6.149696350097656, "genuineness": 4.381826400756836, "identity": 0.5508072376251221, "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_Relief/9809b7cd11bff87a89d391f6ea2d5425e24a104453819d054114953f65e78784.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "988bd3aa5f2581c1924b2f4441672bd83e0471e0b974fa2015df48482c91c1c7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "ae1221bdf971499d8c68048d74a94f848eadbf1b890833706b3062bb4a00dbac", "generation_seconds_batch": 24.347462904988788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18866677582263947, "target_z": -0.2597656293369987, "ce": 6.260893821716309, "genuineness": 4.457139015197754, "identity": 0.6799478530883789, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/988bd3aa5f2581c1924b2f4441672bd83e0471e0b974fa2015df48482c91c1c7.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "98adca232bb30ab81e30a322d140a2394bc3c4edc222da60898868634a320b08", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 129, "seconds_generated": 10.32, "mp3_sha256": "bdedbf17bff5a35fd16773f487046856df2d7807622612ec8880c86f7f27d6e8", "generation_seconds_batch": 24.06975228805095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.0274739265441895, "target_z": 2.3749999786486216, "ce": 6.109982967376709, "genuineness": 4.243753433227539, "identity": 0.626876950263977, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos la.", "wer": 0.23529411764705882, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/98adca232bb30ab81e30a322d140a2394bc3c4edc222da60898868634a320b08.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "98b4ef099692f72490ce02eadfb6cb2a62e2e99cb5ffa45768a0ab5acbe9db31", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8744019130f18a33d3d6d2947607794cdf8e568854643782a129187c612cdf30", "generation_seconds_batch": 32.156592471990734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.767979621887207, "target_z": 0.5703124799830829, "ce": 6.173524379730225, "genuineness": 4.030367851257324, "identity": 0.17328378558158875, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/98b4ef099692f72490ce02eadfb6cb2a62e2e99cb5ffa45768a0ab5acbe9db31.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "98ff73061e7f94064f8fd22ee6f2ec77968556175ad01e8527f323371c3fe02e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "8bbfe752b7f7efaae26d0ff42dff00046d389b9d331e81c1a22d28af76a5339e", "generation_seconds_batch": 20.92794738104567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.789789080619812, "target_z": 0.6015625280236839, "ce": 6.125868320465088, "genuineness": 3.6475296020507812, "identity": 0.25043031573295593, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/98ff73061e7f94064f8fd22ee6f2ec77968556175ad01e8527f323371c3fe02e.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "99204b94d51ac833ce846f9b5b59f376262a1db13776fb9963d97ef0395b0a66", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "90ee1497090a8b887c0796312afc53f359be84f2ac5c9716758c3bb60fdabf11", "generation_seconds_batch": 20.523833681014366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0215141773223877, "target_z": 0.9335937119678575, "ce": 6.149696350097656, "genuineness": 4.2751336097717285, "identity": 0.6200894117355347, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/99204b94d51ac833ce846f9b5b59f376262a1db13776fb9963d97ef0395b0a66.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "e227137e21e136b570de2ba3b9aac20e28a4daf20123083fff0b21c0a3b38f0d", "generation_seconds_batch": 17.818637708900496, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9070147275924683, "target_z": 0.7695312586739974, "ce": 6.38003396987915, "genuineness": 4.507347106933594, "identity": 0.4420662820339203, "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_Relief/99bf1b7d3eed7b885fdae888ab00b4960791c3971d259b46f771306d2801e39b.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": "99c568620153957600c3b15eb4db4f060c548b3bc04bf7440021dd8a2f0504ec", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "a18ca1ebf59823124d47c4ec72e2c826f4aaf838ca04f5ab1b87371af25a16ab", "generation_seconds_batch": 21.21970437199343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6616586446762085, "target_z": 0.4179686879475569, "ce": 6.078212261199951, "genuineness": 4.419482707977295, "identity": 0.5920788049697876, "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_Relief/99c568620153957600c3b15eb4db4f060c548b3bc04bf7440021dd8a2f0504ec.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "9b320a45b6c2b853b1069c9363305e2f542cb7a653b24be75a8dfab1a76f445f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a48da609bdd54f8659682a86206a653fc11915a33a321053fab88b1c25ad3139", "generation_seconds_batch": 26.892150399042293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8906576633453369, "target_z": 0.7460937653463031, "ce": 6.316492557525635, "genuineness": 4.582659721374512, "identity": 0.2876203954219818, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/9b320a45b6c2b853b1069c9363305e2f542cb7a653b24be75a8dfab1a76f445f.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "9b3d570232c35cd7abbfa29722105b8ee00489a3ef13aea295c338fe8dc48a00", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "3dd9e561d649a79f0165220e7ec36e7dd11ec36ed25aa1fb529153d77db20c19", "generation_seconds_batch": 23.088153496966697, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2581843137741089, "target_z": -0.16015626134291971, "ce": 6.0305562019348145, "genuineness": 4.231201171875, "identity": 0.6818166375160217, "hypothesis": "Ik 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_Relief/9b3d570232c35cd7abbfa29722105b8ee00489a3ef13aea295c338fe8dc48a00.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": "9bc1ae26026c10177c91c7ba59a7de7bda5149e013fb8a90087990fd82e5f9da", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wann wir reden können.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Deine Nachricht kam, als ich schon weg war.\n(Natural clear speech.) [3.8 seconds duration] Ich las sie zweimal... dann legte ich das Handy weg.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wann wir reden können.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c9a78c78a0e4afe9d42c5c9b4ea9ca7c82ecec3a174b1790cc4d96f8def6710d", "generation_seconds_batch": 21.590356310014613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9402363300323486, "target_z": 2.2500001281082698, "ce": 6.403861999511719, "genuineness": 4.645420074462891, "identity": 0.6687781810760498, "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_Relief/9bc1ae26026c10177c91c7ba59a7de7bda5149e013fb8a90087990fd82e5f9da.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "9be14934a47eaf48ad3d35fca5bf36e17d24fd8fdba370655716a64793322cbb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "18cad7d4447b8b2a85ac4cb254a2aea08462d0a34f78dec66de26a115c0b1393", "generation_seconds_batch": 16.596530648996122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.722141981124878, "target_z": 1.9374999893243108, "ce": 6.205295085906982, "genuineness": 4.18099308013916, "identity": 0.6049972772598267, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble what 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_Relief/9be14934a47eaf48ad3d35fca5bf36e17d24fd8fdba370655716a64793322cbb.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "877463621600e97a5333a61663c524894fd1ece16f003a9ca57b5291e17daad4", "generation_seconds_batch": 18.456065137987025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.13278011977672577, "target_z": -0.33984376000845856, "ce": 6.221180438995361, "genuineness": 4.3504462242126465, "identity": 0.6107972264289856, "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_Relief/9c09e940c5dab53287ffae2d1a8fa5296f41b2df71714656aaa2bb8830bf5162.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "9c14b4e7f6dc12b99a76d86b0ea3c09e807c04b34408327637c2e3f780ccc8ec", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ea0c87c5888d00fe2cf9d4801eaddb57e1020bec30e0f42fab9deecb67e301f7", "generation_seconds_batch": 19.84973640507087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8661220073699951, "target_z": 0.7109374399492486, "ce": 6.372091293334961, "genuineness": 4.344170093536377, "identity": 0.6307204961776733, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/9c14b4e7f6dc12b99a76d86b0ea3c09e807c04b34408327637c2e3f780ccc8ec.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "9c36f46b9051c160d66d2ee1990b45b3201cd7df274d481fc5cf4a108800fe1a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7b7d6985f4ae1aa5da554b49c971e49049b986210689eec8088c298f567ad38b", "generation_seconds_batch": 24.898162225959823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6725634336471558, "target_z": 0.4335937973733705, "ce": 6.1020402908325195, "genuineness": 3.9927117824554443, "identity": 0.19257068634033203, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/9c36f46b9051c160d66d2ee1990b45b3201cd7df274d481fc5cf4a108800fe1a.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "9c60ba1f4553050c7b2107ea32d38cf0a8fcc02f7820c8c6dcfd713a6968fc16", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "62b9914ad944b0149ab10e1d2a0f9adeb9a35eef20d100c92189039cf7970881", "generation_seconds_batch": 27.32812126900535, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.059680700302124, "target_z": 0.9882812533361529, "ce": 6.149696350097656, "genuineness": 4.6203155517578125, "identity": 0.7257971167564392, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/9c60ba1f4553050c7b2107ea32d38cf0a8fcc02f7820c8c6dcfd713a6968fc16.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "664279c2eebebb68cf309ec4bedd2e8a1c67e840575d6d73cb131f7aedc95d12", "generation_seconds_batch": 16.892100521014072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.16413117945194244, "target_z": -0.29492186932854014, "ce": 6.054384231567383, "genuineness": 4.482243061065674, "identity": 0.6174330115318298, "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_Relief/9c969db20a6db380e08592f6aed9c9189b3db634d677ebe8f573f593ebdfd2d3.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": "9ccd235fba44668fe631d758c4105e0f23783e6820aa1e48931e388da1864c93", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7172fc0d4a24bd9ca8dacb8617386d4a454a7f33899b5a572dc4c63eaa219753", "generation_seconds_batch": 20.300306031946093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5539746284484863, "target_z": 0.2636718426393173, "ce": 6.1894097328186035, "genuineness": 4.419482707977295, "identity": 0.7541546821594238, "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_Relief/9ccd235fba44668fe631d758c4105e0f23783e6820aa1e48931e388da1864c93.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "9dcd620593b8b6602ffc0689d8953e0e12c70157656956855fb591b27743ab01", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e46110c79a756659fb501c09700de80650854584db437ccba1d0aef140142efd", "generation_seconds_batch": 16.55951545003336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1136968731880188, "target_z": -0.367187509341228, "ce": 6.221180438995361, "genuineness": 4.394378662109375, "identity": 0.7221314907073975, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/9dcd620593b8b6602ffc0689d8953e0e12c70157656956855fb591b27743ab01.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "9df852234cb6cafe4bb7b5fc76f2b0a48ba377974a8b4e5c91ff78504e6bedd1", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "3099cfa57a0b86d4e99540b85d089491e537f36ef9f45291bde8a6de14f977bd", "generation_seconds_batch": 20.177506292006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.08916127681732178, "target_z": -0.40234374933276945, "ce": 6.173524379730225, "genuineness": 4.168440818786621, "identity": 0.3203568458557129, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/9df852234cb6cafe4bb7b5fc76f2b0a48ba377974a8b4e5c91ff78504e6bedd1.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": "9e43e7c4c1fe247813440394bfcf4c339aa32ad4f59fd04f65d4c2e17503703d", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e9966da82e9f11c77504605a8e014f6cae6caeeefaee4b3e8acdf4f40bfa0011", "generation_seconds_batch": 18.320680011995137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31270790100097656, "target_z": -0.08203122664693002, "ce": 6.332377910614014, "genuineness": 4.8588056564331055, "identity": 0.6841458082199097, "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_Relief/9e43e7c4c1fe247813440394bfcf4c339aa32ad4f59fd04f65d4c2e17503703d.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "9e57e1bf6c1f940d5db23ae7fb83880d4054b7489f31620bef2e097ce8125eaf", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "73a08d117b6afe3ec8fc2021e2ae0f4b85fea2607cbc806c76e3a89f58b6a1a0", "generation_seconds_batch": 23.790454932954162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40948721766471863, "target_z": 0.05664063734376556, "ce": 6.062326908111572, "genuineness": 4.632867813110352, "identity": 0.5934809446334839, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/9e57e1bf6c1f940d5db23ae7fb83880d4054b7489f31620bef2e097ce8125eaf.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "9e9f9665251f0172b2ca3e4f11967e6d0a27184dd4edf639b8fc61fd67a27a63", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "295b06fbb74305fd6a2cd6131cc7d9042d8884c854b842d970762675d4af0bbc", "generation_seconds_batch": 22.72691460698843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6125874519348145, "target_z": 0.34765620796447405, "ce": 6.268836498260498, "genuineness": 4.306513786315918, "identity": 0.21382731199264526, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/9e9f9665251f0172b2ca3e4f11967e6d0a27184dd4edf639b8fc61fd67a27a63.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "9f0485c84bb21f14a9de7a3f76c1eee60d50b0eee9f8fee230dcfb13c17051fd", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ed98784fdfeca89308f5a38ee6fce8944e5c92e64f5d987ee6a9b48303a8e5a0", "generation_seconds_batch": 23.230745112989098, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0569545030593872, "target_z": 0.9843749759796995, "ce": 5.792276382446289, "genuineness": 3.986435890197754, "identity": 0.6133130788803101, "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_Relief/9f0485c84bb21f14a9de7a3f76c1eee60d50b0eee9f8fee230dcfb13c17051fd.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "9f53b5fcfb5576f71b19f18062274c85fac2438b2bd7a0fe6baabdcfd04e5052", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "48a6698be87c5c2bc6913fce174221ab64abd96a43dbfad53f131f914e750b46", "generation_seconds_batch": 16.840185210923664, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1278351545333862, "target_z": 1.0859375040033834, "ce": 6.292664527893066, "genuineness": 4.2249250411987305, "identity": 0.5885881185531616, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam.", "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_Relief/9f53b5fcfb5576f71b19f18062274c85fac2438b2bd7a0fe6baabdcfd04e5052.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "a0b189dff69479790b64583513dfc6e31549d822ab629f5ce30f0a5471d14c25", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "028b751b6d8ee70d99b15de814d3b697f4328bfc82ae2835940efe8e6bc90c8d", "generation_seconds_batch": 19.84973640507087, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5635162591934204, "target_z": 0.2773437279813912, "ce": 6.197352409362793, "genuineness": 4.645420074462891, "identity": 0.7340571880340576, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a0b189dff69479790b64583513dfc6e31549d822ab629f5ce30f0a5471d14c25.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "a0b6b10b2199e0ab2e31eb6330905beacfc7d0939ce7c2e00e0d9f374c490e88", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "0cdc8f6ae3b94bdbf853c84da6d70dd921fa12a7759ad4fcd8e3524de47d6dcf", "generation_seconds_batch": 21.39308056398295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37949925661087036, "target_z": 0.013671885342073847, "ce": 6.0146708488464355, "genuineness": 4.413206577301025, "identity": 0.6584793329238892, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a0b6b10b2199e0ab2e31eb6330905beacfc7d0939ce7c2e00e0d9f374c490e88.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": "a0d1170a09fdc5768f9d4d53739edb1099bace923b868b386ec0212d140e3ef4", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Call me when you have a moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I wrote the number on the envelope.\n(Natural clear speech.) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Natural clear speech.) [3.2 seconds duration] Call me when you have a moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9c0c521e55e7cb7b05f84066096f4bb89eba35da3923473a21bdce777be9de4a", "generation_seconds_batch": 17.522399508045055, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5417068600654602, "target_z": 0.24609376534630312, "ce": 6.300607204437256, "genuineness": 3.860914945602417, "identity": 0.34964680671691895, "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_Relief/a0d1170a09fdc5768f9d4d53739edb1099bace923b868b386ec0212d140e3ef4.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": "a0d7e8f9a7c3a069f460aa96fd923b57b4940f58a6803376b5db37057d08e47f", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8eb2c4c3bfcbc639ade4a17211cbe6ff5ea8804cdcbdc55a58a12f29acd6b63f", "generation_seconds_batch": 17.302961291978136, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38801854848861694, "target_z": 0.025878895324099403, "ce": 6.308549880981445, "genuineness": 4.413206577301025, "identity": 0.3824494481086731, "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_Relief/a0d7e8f9a7c3a069f460aa96fd923b57b4940f58a6803376b5db37057d08e47f.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "a1c9a10aad9bd24266d6e3b7c6fd791855ba3a2545953c974cf864a1d80c5dbe", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "833bae45de485a4db82e6915cbd98553bec920db85255dc68caf24b739add249", "generation_seconds_batch": 23.192078102962114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3895483016967773, "target_z": 1.4609375680575183, "ce": 6.332377910614014, "genuineness": 4.632867813110352, "identity": 0.4403916597366333, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a1c9a10aad9bd24266d6e3b7c6fd791855ba3a2545953c974cf864a1d80c5dbe.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "a1f4783db49d0bc48f3ed42f420926669a1e699186e87e7775012c1e434741e7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "16101d01611f8b0147da88a18a0ccffc79367a331234c8e1451ebc7bc9dff295", "generation_seconds_batch": 18.484454660094343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4767858982086182, "target_z": 1.5859374185978703, "ce": 5.879645347595215, "genuineness": 4.093128204345703, "identity": 0.5352469086647034, "hypothesis": "La puerta sigue abierta y he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a1f4783db49d0bc48f3ed42f420926669a1e699186e87e7775012c1e434741e7.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "a290a5e6348d2314d5b8b4f95ec8c9bdda45f616920cd21a8ab042d0ed072440", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9f6549e73ceff8603c2e5586eb2512ada5a76a22d0c97a3aeef0199c6f25e69c", "generation_seconds_batch": 24.75546178605873, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9206455945968628, "target_z": 0.7890624746452383, "ce": 6.332377910614014, "genuineness": 4.557555198669434, "identity": 0.634353518486023, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a290a5e6348d2314d5b8b4f95ec8c9bdda45f616920cd21a8ab042d0ed072440.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": "a353b2d67c4050d0107bbc8f7435c9b4b5842b3da671575363acc7238708baad", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f672e6831b79eb760bbc50c3bc61d5310b3bb85b9e12ba26ab21b25bb953b687", "generation_seconds_batch": 18.399398664943874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4255034923553467, "target_z": 0.07958982465052492, "ce": 6.24500846862793, "genuineness": 4.3504462242126465, "identity": 0.5893476605415344, "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_Relief/a353b2d67c4050d0107bbc8f7435c9b4b5842b3da671575363acc7238708baad.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "a3f6d35f85fa08eba0938ac5ad4db5137656f3ff65bb8eb1ac513400bd38eba2", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 1.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6af0ba1ef918f2ddc2e3af172fc06f35fa2350c75ec18c298821079f5bace3f0", "generation_seconds_batch": 24.24680736591108, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4081241190433502, "target_z": 0.05468749866553886, "ce": 6.499174118041992, "genuineness": 4.432034492492676, "identity": 0.38695552945137024, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a3f6d35f85fa08eba0938ac5ad4db5137656f3ff65bb8eb1ac513400bd38eba2.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "a45bbf47219bf1b11e54a2f53b9eacb0ff3a0cd037462e275cdd4d868d80d69d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d0c5b78563ba8874bd66e2a0492362f6e210560db8869936837f6741e0ac1fd5", "generation_seconds_batch": 21.916149997967295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6044089794158936, "target_z": 0.33593754670613996, "ce": 6.475345611572266, "genuineness": 4.231201171875, "identity": 0.40582549571990967, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a45bbf47219bf1b11e54a2f53b9eacb0ff3a0cd037462e275cdd4d868d80d69d.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "a54ba91607be61b16a2b2d6a44e2ca74697a9a03d16929b51daffca54131ab78", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "adfeddcd97cef7c0a1cb35556b0fe4a03ce0bcc259f462edc1594ea363ace7ab", "generation_seconds_batch": 23.263297195080668, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8334078788757324, "target_z": 0.66406245329386, "ce": 6.0305562019348145, "genuineness": 4.13078498840332, "identity": 0.6962356567382812, "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_Relief/a54ba91607be61b16a2b2d6a44e2ca74697a9a03d16929b51daffca54131ab78.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "a62d65e508a5b53486148a2166066305001e19fd1e84f87e9630427f64437062", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "9eebd1a8ac9236bfa54cd16a58fafecc3bb48accb656fa5f2bfea4746f6cb643", "generation_seconds_batch": 24.371509975986555, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7734320163726807, "target_z": 0.5781250346959896, "ce": 6.173524379730225, "genuineness": 4.256305694580078, "identity": 0.7709438800811768, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a62d65e508a5b53486148a2166066305001e19fd1e84f87e9630427f64437062.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "a697df414143f434ab482587cc1fa586ac2a7ac6da11d5b9e30e849b73471c03", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1e5ddaf03f95fe994527519765f221e7dc4a48634f3b587b0584707ed2c96f6d", "generation_seconds_batch": 21.39308056398295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2391010820865631, "target_z": -0.18749998932431086, "ce": 6.070269584655762, "genuineness": 4.306513786315918, "identity": 0.6255972385406494, "hypothesis": "Ik heb het kleine doosje gevonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a697df414143f434ab482587cc1fa586ac2a7ac6da11d5b9e30e849b73471c03.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": "a6b2d45dec7a92cf8e75f9e63b24736eee0fc1382ffd7b196790f8ec9ac588c6", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9431524b7b7f25c83a3afff570807fc4b005d455fa1d795709d7f07a0933db7a", "generation_seconds_batch": 20.393640883034095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3358803987503052, "target_z": -0.04882812533361529, "ce": 6.324435234069824, "genuineness": 4.482243061065674, "identity": 0.6897852420806885, "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_Relief/a6b2d45dec7a92cf8e75f9e63b24736eee0fc1382ffd7b196790f8ec9ac588c6.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": "a6e271a4b92e56d0187aa588a979239589c459e7d16bb235d0bdfb05ed0eb3d2", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3592e496ecaa4573d34233b79dd477eba5eb0bca1acd0ad7dcc18c9654f5bd8b", "generation_seconds_batch": 17.433295511989854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9479073882102966, "target_z": 0.8281249919932332, "ce": 5.7684478759765625, "genuineness": 4.457139015197754, "identity": 0.6228193044662476, "hypothesis": "Ju numero sur l'enveloppe. Lise le bien et verify les deux derniers chiffres. Appel moi quand you're a moment.", "wer": 0.45454545454545453, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a6e271a4b92e56d0187aa588a979239589c459e7d16bb235d0bdfb05ed0eb3d2.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "a721b9216f9594d38bde12c7b368c2229c69f14f480e22cb7f6bf770caca49ab", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "82ccd06e9407419a599f36c221fda9d2ab660255393cfc004619616374c01799", "generation_seconds_batch": 16.596530648996122, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7112371921539307, "target_z": 1.9218748798984973, "ce": 6.181467056274414, "genuineness": 4.444586753845215, "identity": 0.7483649253845215, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a721b9216f9594d38bde12c7b368c2229c69f14f480e22cb7f6bf770caca49ab.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "a74f2ada5b04830ea1aef9d586de9712ca073181aab22c45be7408217d77ea76", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "8b88b5409bc3a575e6321eb3f740a3b8266f45fe3c0c1382f33fed7716c787db", "generation_seconds_batch": 24.039762314991094, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9751691818237305, "target_z": 0.867187509341228, "ce": 5.855817794799805, "genuineness": 4.482243061065674, "identity": 0.6532928943634033, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a74f2ada5b04830ea1aef9d586de9712ca073181aab22c45be7408217d77ea76.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "a7746203c6719b23f99e5c00d8f17cb5aa8894b87051b09586a22e40ed4911e8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2a0c6587c0e5239f8432daf6cf2b895181f75c4d257c5af7b6845acb9c409de1", "generation_seconds_batch": 16.353198898024857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.12869085371494293, "target_z": -0.34570313334038216, "ce": 6.2767791748046875, "genuineness": 4.3127899169921875, "identity": 0.7427613735198975, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a7746203c6719b23f99e5c00d8f17cb5aa8894b87051b09586a22e40ed4911e8.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "a82448f5d8b9ba5d2630836b03dc1c93604acb94c953a74c22e3d7f0e8bce13b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ff53e016b3618c6e16d1069fa3ebd72d1da92068dac279945f0730d0e358181c", "generation_seconds_batch": 24.673941436922178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1368694007396698, "target_z": -0.33398436532515674, "ce": 5.990842819213867, "genuineness": 4.256305694580078, "identity": 0.5958119630813599, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a82448f5d8b9ba5d2630836b03dc1c93604acb94c953a74c22e3d7f0e8bce13b.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "2f66cd8dfa747037b7aa869a4440ebccc1e8da3da79211ee6ff0e06752a8b04e", "generation_seconds_batch": 18.64568368392065, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.02100682258605957, "target_z": -0.5, "ce": 6.173524379730225, "genuineness": 4.3881025314331055, "identity": 0.6464860439300537, "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_Relief/a8bd001b1fcafd2f49b65d73e6ed12567e4c9664909a4d08700c9febfd977540.mp3" }, { "id": "heldout-fr-0", "language": "fr", "sentences": [ "Ton message est arrivé après mon départ.", "Je l’ai relu... puis j’ai rangé mon téléphone.", "Dis-moi quand nous pourrons parler." ], "text": "Ton message est arrivé après mon départ. Je l’ai relu... puis j’ai rangé mon téléphone. Dis-moi quand nous pourrons parler.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "heldout-fr-0", "key": "a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea", "bucket": "emo_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "f25701db2a611ebc19da8d63cd1c73efac5ad943f17f3812790fa520948f1621", "generation_seconds_batch": 17.07953952299431, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8715744018554688, "target_z": 0.7187499946621554, "ce": 6.213237762451172, "genuineness": 4.375550270080566, "identity": 0.8181924819946289, "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_Relief/a94b7d5da78ff217f8e5a4f7ae4520900bef0ad764d0e4ee898e69de10c28aea.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "a98ecf5720f033238681403ea494858b8034fbde435576d7bc630aa03f972f1f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "1d37c9f0456f6aefc4eece192e99afd0729e7c366df88cfe4ddfae7a4fd6fb8e", "generation_seconds_batch": 17.878418394946493, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4858202040195465, "target_z": 0.1660156346748433, "ce": 6.062326908111572, "genuineness": 3.8671910762786865, "identity": 0.37911632657051086, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a98ecf5720f033238681403ea494858b8034fbde435576d7bc630aa03f972f1f.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "a9c01392c978041006d48df7281066a1a00808332a80cb384d4ccaf6004509d6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "d7e8798f150dc220258f4d8f5f1cb498a708e5692c85eba1965f8146a836a898", "generation_seconds_batch": 28.998471656115726, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3023104667663574, "target_z": 1.3359373758951139, "ce": 6.395919322967529, "genuineness": 4.494794845581055, "identity": 0.34738433361053467, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/a9c01392c978041006d48df7281066a1a00808332a80cb384d4ccaf6004509d6.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "aa917df2d98527a281596409eed57979ce3bf25e16543538a2e470c94dea9370", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "6e07614955c4fefb477a3709fb1760c3e4f55a4c69fbf8742b87e4724dc5937f", "generation_seconds_batch": 24.407364869024605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4176657497882843, "target_z": 0.06835938400761271, "ce": 6.475345611572266, "genuineness": 4.482243061065674, "identity": 0.5468801856040955, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/aa917df2d98527a281596409eed57979ce3bf25e16543538a2e470c94dea9370.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "53c3a5b13646734a86bb553f7385f245f0acfc619ddd1dcb6945f2a5b54f5972", "generation_seconds_batch": 18.659329934045672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3852923810482025, "target_z": 0.02197266067040253, "ce": 6.443574905395508, "genuineness": 4.105680465698242, "identity": 0.39651456475257874, "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_Relief/ab7a94299f968552a7b966fa3391724b652d8e20483888a7767196f29a7f4a69.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "abd3e6fa93c8bea231a54069bec91f0918e8f8d0cef25f7fb8b834828fd76d60", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.5, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9e132d5c1ea01c479913798d3adcd2b55626b38b3f5021f58fedac58af933a43", "generation_seconds_batch": 25.70037372491788, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9042885303497314, "target_z": 0.765624981317544, "ce": 6.252951145172119, "genuineness": 4.444586753845215, "identity": 0.7224777340888977, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/abd3e6fa93c8bea231a54069bec91f0918e8f8d0cef25f7fb8b834828fd76d60.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": "ac9bb6275ae029160304117cea89ba89e80f6803c4cb3c67e5778a7ddfabd73f", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "517ac1b80fc08ab25487ca0562354c8098e4f5c0bbede6d00cc4328cbd17ae15", "generation_seconds_batch": 25.59593162301462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6453015804290771, "target_z": 0.39453119461986264, "ce": 6.252951145172119, "genuineness": 4.582659721374512, "identity": 0.8800461292266846, "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_Relief/ac9bb6275ae029160304117cea89ba89e80f6803c4cb3c67e5778a7ddfabd73f.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "aca216fec12cb4ac4cf91046b6abc7d1fd1ecfa5835bd26be79fbb33bc775e78", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "7356830b4f73d07185ab2dd73591e954fec510afd6f8080a74c07486ed5df6b0", "generation_seconds_batch": 17.453031396958977, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6534801721572876, "target_z": 0.40625002668922283, "ce": 6.205295085906982, "genuineness": 3.8420867919921875, "identity": 0.34510037302970886, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/aca216fec12cb4ac4cf91046b6abc7d1fd1ecfa5835bd26be79fbb33bc775e78.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": "ad36ceaac1dbec149585ce4b4b46e7cb24dcdd65ce83ae3fdced54f56dc9ce1a", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "065f0efd963c8fb7c4e1115482a7f8950149e5dd88d9cdb7d8c2d017ab001e26", "generation_seconds_batch": 18.115210441988893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33213189244270325, "target_z": -0.05419923534736045, "ce": 6.427689552307129, "genuineness": 4.557555198669434, "identity": 0.7111605405807495, "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_Relief/ad36ceaac1dbec149585ce4b4b46e7cb24dcdd65ce83ae3fdced54f56dc9ce1a.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "ad9038a1376a31db21e28982cc4133ff21b57d110c082ec19c22baf1b67d1a6d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3b130c2815807b1ad01f6d7d91536c692806f36216f5e7f81f2cbea29beba310", "generation_seconds_batch": 24.22604095400311, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2919207811355591, "target_z": -0.11181639932748283, "ce": 6.1020402908325195, "genuineness": 4.319066047668457, "identity": 0.7106143236160278, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ad9038a1376a31db21e28982cc4133ff21b57d110c082ec19c22baf1b67d1a6d.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "8b45e73ac6b98dc5fc7f64b9a804ee947df0306194de2220d3b425cff92ce373", "generation_seconds_batch": 19.990200657979585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5253497958183289, "target_z": 0.22265627201860883, "ce": 6.2767791748046875, "genuineness": 4.557555198669434, "identity": 0.5802039504051208, "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_Relief/adcc0121d6c11de6953f8243f84ad890832f75283c96342c1db246fddc443438.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "addbb693bed37951079a8436cafaddcc14c81a1c7b27e2ca3268f497c4ccdb99", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "58b65fdbade0fc5cdf2e4457ae4605fdf83698887c4afb1b731af3b65605aca0", "generation_seconds_batch": 24.205844998010434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3515559136867523, "target_z": -0.026367201345034345, "ce": 6.403861999511719, "genuineness": 4.519899368286133, "identity": 0.558603048324585, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/addbb693bed37951079a8436cafaddcc14c81a1c7b27e2ca3268f497c4ccdb99.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": "ae1be395aada13bc26303240b240ada6035c1884c3f3ee78170b3289fda53ab5", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f40cd6fd71ee6b3eb810060a98974b1e59de7fd69d9a071f8a8324bb2f59f15", "generation_seconds_batch": 24.797952094930224, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5328467488288879, "target_z": 0.2333984066405861, "ce": 6.324435234069824, "genuineness": 4.331617832183838, "identity": 0.5524429082870483, "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_Relief/ae1be395aada13bc26303240b240ada6035c1884c3f3ee78170b3289fda53ab5.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "f0bfda02d9d39648f216fc7cf1784fc42312446cbd6ceaf8a5fa19f963e44bb2", "generation_seconds_batch": 17.663099194993265, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20638693869113922, "target_z": -0.23437499733107772, "ce": 6.38003396987915, "genuineness": 3.9550557136535645, "identity": 0.5345596671104431, "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_Relief/ae3130a5db36c2790a31e23135fde257111c56fa9c5b8061c1f3e51a8cb61258.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": "ae875e58f99cbb64d7a4fc46d7e647cc2a8349a0cd91e3c9fe55b0a1a7d13478", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Natural clear speech.) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Natural clear speech.) [3.2 seconds duration] Nous la remettrons après le déjeuner.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7fd127670d56f528be1de28fba6ab21daf34a2d091fc4385ecb54979c3760d9a", "generation_seconds_batch": 18.704130155965686, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6998251676559448, "target_z": 0.4726562293158523, "ce": 6.149696350097656, "genuineness": 4.507347106933594, "identity": 0.8171583414077759, "hypothesis": "Kelka deplaced the petite chaise blew. Elle is ici, pretty la grand bibliothèque.", "wer": 0.7142857142857143, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ae875e58f99cbb64d7a4fc46d7e647cc2a8349a0cd91e3c9fe55b0a1a7d13478.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "ae95aefc64ea10b448a3784410595cf0cf5491abb1309435e9829f280b25a3b4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "843f6f6c8ce66037ef71be6bc7d76a79870e3c6212a19afcf4592213299097b9", "generation_seconds_batch": 23.966249189921655, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.067859172821045, "target_z": 0.9999999145944869, "ce": 6.149696350097656, "genuineness": 4.105680465698242, "identity": 0.5546938180923462, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ae95aefc64ea10b448a3784410595cf0cf5491abb1309435e9829f280b25a3b4.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": "aeedf41a12e43faa85ceb42b80de618e6b1853c23bb2cfe4a59d7aa2f156b69f", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2a9e4595e76e0dfc7664b9f96e75460de684740ebc232dfc1bb4a208d479362b", "generation_seconds_batch": 16.07511752191931, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.718908429145813, "target_z": 0.5, "ce": 6.348263263702393, "genuineness": 4.287685871124268, "identity": 0.1939696967601776, "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_Relief/aeedf41a12e43faa85ceb42b80de618e6b1853c23bb2cfe4a59d7aa2f156b69f.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "af2227c668d00bc4600abfb1c16aa8fee9d12a0f16bd1465f6ee7c1a0e9a25da", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a0cc4b4c73c4b25ccdc414c713e4bcb98388603d2f239c6a0a289eceff43efde", "generation_seconds_batch": 25.097826470038854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4473129212856293, "target_z": 0.11083982998836947, "ce": 6.221180438995361, "genuineness": 4.20609712600708, "identity": 0.5223160982131958, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/af2227c668d00bc4600abfb1c16aa8fee9d12a0f16bd1465f6ee7c1a0e9a25da.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "af7903ec3bbe8f8b1b623913d8614396216957ddb1602e313d8ca43f44b3ada7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "4557d263639c2ab3b0a0b63f9171b994fcacc097dd2eeb5e08edc179833bfebc", "generation_seconds_batch": 24.07032531197183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6630218029022217, "target_z": 0.4199219120312967, "ce": 6.316492557525635, "genuineness": 4.369274139404297, "identity": 0.2833264470100403, "hypothesis": "The 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_Relief/af7903ec3bbe8f8b1b623913d8614396216957ddb1602e313d8ca43f44b3ada7.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "afcd2c9b37b806e7b37b19262a5fcea0ac8a93ba3efa28d22e7da1f738fd560b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "afea0dfe18b16ec4ad10c54bd4633e88beac66c753fc93c38b1514fa22cf5bb2", "generation_seconds_batch": 21.783989766030572, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3840959072113037, "target_z": 1.4531250133446114, "ce": 6.292664527893066, "genuineness": 4.457139015197754, "identity": 0.3664584755897522, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/afcd2c9b37b806e7b37b19262a5fcea0ac8a93ba3efa28d22e7da1f738fd560b.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "afd62b406a766a9cde13d0b3a16bd3cc2e93f0c0c2e07ad9e6aa1dba20c574ca", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "5aab9747b4e68e87f699476604816dadd586dda5354bb7690f7077fb39c786c2", "generation_seconds_batch": 22.158343469025567, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4946802854537964, "target_z": 0.17871095067780376, "ce": 6.467403411865234, "genuineness": 4.174716949462891, "identity": 0.4901597499847412, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/afd62b406a766a9cde13d0b3a16bd3cc2e93f0c0c2e07ad9e6aa1dba20c574ca.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "b089f7c63fe5da3eafb2d3e3efe72c632e7974c4b92ae05d8b452721ac1ad91a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9277da1e231804aeb09df67e08efba7e540b38b02ee17ab8c19052839ff84fbd", "generation_seconds_batch": 32.19138946698513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3587121367454529, "target_z": -0.016113287338478957, "ce": 6.229123115539551, "genuineness": 4.532451152801514, "identity": 0.682611346244812, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b089f7c63fe5da3eafb2d3e3efe72c632e7974c4b92ae05d8b452721ac1ad91a.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "b09356756937d0232dd830c855ac6a31de9b2a21be1c6ce64111c0ac58dee779", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "57a574c13ca3e524339303a41d0642efbac64dfd452f55ba63a0a90277d730cd", "generation_seconds_batch": 23.856130195083097, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9206455945968628, "target_z": 0.7890624746452383, "ce": 6.252951145172119, "genuineness": 4.356721878051758, "identity": 0.7307212948799133, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b09356756937d0232dd830c855ac6a31de9b2a21be1c6ce64111c0ac58dee779.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "b0ea5c76b9b2efb4c373baa9b4f2e9a0ca068776d0f119ba3f6c99bd472c199f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "76193f95c812221b6ff9adabbe41682f5f2119f5c8000720e614d6954bc4f693", "generation_seconds_batch": 16.302759237005375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34269583225250244, "target_z": -0.03906251734799484, "ce": 6.125868320465088, "genuineness": 4.2249250411987305, "identity": 0.48911744356155396, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b0ea5c76b9b2efb4c373baa9b4f2e9a0ca068776d0f119ba3f6c99bd472c199f.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "b14547002cdddcdf5f1a47e7c3f57630ee3dd9c97bee9c35b27b6a37a2fe01d6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "e05be3a6c0b73e471426d097761a47b90efe6d6698f0d7ba780ff6ec8bb5f2c8", "generation_seconds_batch": 18.49221270403359, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3737061321735382, "target_z": 0.005371110013745163, "ce": 5.935244083404541, "genuineness": 4.256305694580078, "identity": 0.314430296421051, "hypothesis": "De deur 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_Relief/b14547002cdddcdf5f1a47e7c3f57630ee3dd9c97bee9c35b27b6a37a2fe01d6.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "b1a9bb0e21be913355f23a5033d5d10cc3bb47e4483fbd442e6c5dc25f340f4c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "3a55b1a7ece7c844f9d44896f385e3f87c6ed0d8c1f3100a70092b53b628af50", "generation_seconds_batch": 21.99052685010247, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.08966863155365, "target_z": 1.031249962635088, "ce": 5.982900142669678, "genuineness": 4.099404335021973, "identity": 0.5459465980529785, "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_Relief/b1a9bb0e21be913355f23a5033d5d10cc3bb47e4483fbd442e6c5dc25f340f4c.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "b22bb4f44973e1c2b491a72efca2710aafa0738a4d2cad402f1685bab9a09889", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "57d8266875132e38e5358c2f95f1bc1b78698cf3ae54e89e9479d2d9249038d9", "generation_seconds_batch": 22.29736952704843, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8857126235961914, "target_z": 2.171874922601254, "ce": 6.260893821716309, "genuineness": 4.2374773025512695, "identity": 0.7600793838500977, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b22bb4f44973e1c2b491a72efca2710aafa0738a4d2cad402f1685bab9a09889.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "b2d74b8ac48a65d5457c9d927bd2420932d1f8b23e5652b200ede35e9d1bb78e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "b3085141ead86fa9c7e1442adc6115fcf8b12af32229120ab6ee4fd442541e91", "generation_seconds_batch": 23.572377271018922, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.498088002204895, "target_z": 0.183593754670614, "ce": 6.054384231567383, "genuineness": 4.061748504638672, "identity": 0.6261141300201416, "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_Relief/b2d74b8ac48a65d5457c9d927bd2420932d1f8b23e5652b200ede35e9d1bb78e.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "b39619b48181e5f229ca06e381ec3246361046b768a53f3e435fb3fe775e4e18", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5cc28cfe810c0f37b1cd4323331b9fce0ff3e4078d3ef413aae6a0f13e250e53", "generation_seconds_batch": 21.52875512908213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18457750976085663, "target_z": -0.2656250026689223, "ce": 6.1894097328186035, "genuineness": 4.344170093536377, "identity": 0.768526017665863, "hypothesis": "De deur staan nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b39619b48181e5f229ca06e381ec3246361046b768a53f3e435fb3fe775e4e18.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "b4240efe13a9db68223431e71324ee5d1d184f281bb806e737d17cb2def32d04", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "1939e922a78719842189016a5df4f90844ae4a1ea707388401f17c6e76a42488", "generation_seconds_batch": 16.302759237005375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22274400293827057, "target_z": -0.21093750400338343, "ce": 6.372091293334961, "genuineness": 4.645420074462891, "identity": 0.5007827281951904, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b4240efe13a9db68223431e71324ee5d1d184f281bb806e737d17cb2def32d04.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "7ed40e483a0697d5700c202fd0fb5a70bd808f4597a61bb94b2e5214dd5b4822", "generation_seconds_batch": 17.063584667048417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20093457400798798, "target_z": -0.24218750934122799, "ce": 6.292664527893066, "genuineness": 4.432034492492676, "identity": 0.5990191102027893, "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_Relief/b429ad869b4f073af736e4e6510807542fc4f5324b0eb7f096c719d9002f4f71.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "b43713b778dc0107ac7bef813e6bfbaa4be9255eeec9088dd301b58e6cc93cde", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "058b19e04448e45cb8e2ee3e51422765f9963f14fa8a1b32eccbf51d1ae73b3e", "generation_seconds_batch": 27.602871821960434, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4822382926940918, "target_z": 1.5937499733107772, "ce": 6.24500846862793, "genuineness": 4.3504462242126465, "identity": 0.3501625061035156, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b43713b778dc0107ac7bef813e6bfbaa4be9255eeec9088dd301b58e6cc93cde.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "b4bcfea1b60e2d5d16530da136efb108d0410df2dd765845f3ba7624b327df7e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c1a70035e6f989ccb61bb677472da6664cf2e05201c6a3fca13a7f23e3146340", "generation_seconds_batch": 24.138400629046373, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.181851327419281, "target_z": -0.2695312586739974, "ce": 6.157639026641846, "genuineness": 4.507347106933594, "identity": 0.7909762859344482, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen het er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b4bcfea1b60e2d5d16530da136efb108d0410df2dd765845f3ba7624b327df7e.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "b4d85e4290cc2e8ed4cc2dceba72863697e18b425b08eba577724369eee02631", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": 129, "seconds_generated": 10.32, "mp3_sha256": "12927e827bd61089535d56a5278bf1204d58210e17d2053ea5866e177226501e", "generation_seconds_batch": 22.052578244940378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1005733013153076, "target_z": 1.0468749012498755, "ce": 5.879645347595215, "genuineness": 3.6475296020507812, "identity": 0.5969825983047485, "hypothesis": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo está.", "wer": 0.13333333333333333, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b4d85e4290cc2e8ed4cc2dceba72863697e18b425b08eba577724369eee02631.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": "b5691a08d2ac2f93d41514a75f6d496bb0f6f1b648bfc4e5abb62b755d7eb1c9", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "00d48696f826bf96b545ff5c5fbfd534da3bc6d3ecf9b69d23dcc1cd2d24981e", "generation_seconds_batch": 16.07511752191931, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5212604999542236, "target_z": 0.21679685598392873, "ce": 6.443574905395508, "genuineness": 4.231201171875, "identity": 0.3640632629394531, "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_Relief/b5691a08d2ac2f93d41514a75f6d496bb0f6f1b648bfc4e5abb62b755d7eb1c9.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "b57237bc07bae24ae19bf3ace20e4b7c91f7a641d356ca96cd33c644f9edd425", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "b57214f50e20e3bd5eb4c6f4c1ca5d070a996fdd44dbe62f31b06d53521d0322", "generation_seconds_batch": 23.940178786986507, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7652534246444702, "target_z": 0.5664062026266294, "ce": 6.141753673553467, "genuineness": 4.68307638168335, "identity": 0.42699286341667175, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b57237bc07bae24ae19bf3ace20e4b7c91f7a641d356ca96cd33c644f9edd425.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "b5fc59c71e8eb925e04760cc537710ac7244480b7f00d8511e7f00b8194b9282", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9dc66af33fbb9556736f0cb11fb777bb348d18ae33e8580fe99f5d17e2c18101", "generation_seconds_batch": 22.550550703075714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3895483016967773, "target_z": 1.4609375680575183, "ce": 6.149696350097656, "genuineness": 4.482243061065674, "identity": 0.6454821228981018, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b5fc59c71e8eb925e04760cc537710ac7244480b7f00d8511e7f00b8194b9282.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "b673f3bedee1c5ecd8871daecdcc1159cbba85d5279d425b9ca976d61bebf015", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "1b3e4d0952370b46e8a0432c56dd1969b6df4e2388352877c97a7688d2c7216b", "generation_seconds_batch": 24.30738679692149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7330467700958252, "target_z": 1.9531250987501245, "ce": 6.038498878479004, "genuineness": 4.13078498840332, "identity": 0.5339388847351074, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b673f3bedee1c5ecd8871daecdcc1159cbba85d5279d425b9ca976d61bebf015.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "b785863738bb7bbf3ea33156beb224129acada07ccf29c42f7fc41a0c644840a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "053752d9c0528a8135b0198a0870733cabde592c726b609bf230b711b6594ddc", "generation_seconds_batch": 25.366173141053878, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32361260056495667, "target_z": -0.06640624532938601, "ce": 6.070269584655762, "genuineness": 4.1998209953308105, "identity": 0.6199533343315125, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b785863738bb7bbf3ea33156beb224129acada07ccf29c42f7fc41a0c644840a.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "b7b197cce8569e30b1833ba7ef09264056a9a9a08d56414653945dc54d9c6186", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "20780e056c06852262774131e294439abe5c7455c06a736a396886aadafd9354", "generation_seconds_batch": 24.25185312097892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7788843512535095, "target_z": 0.5859375040033834, "ce": 6.348263263702393, "genuineness": 4.394378662109375, "identity": 0.3813971281051636, "hypothesis": "The 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_Relief/b7b197cce8569e30b1833ba7ef09264056a9a9a08d56414653945dc54d9c6186.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": "b8bda3818a30ee8fb30a6aa373934ebd9190c0b51a6b40c653fbfd5809215275", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "202c962c20f7c24f885c93ab2c22da32292ccf8a5f3cd7e485337b010bf4648c", "generation_seconds_batch": 19.39999489299953, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6752895712852478, "target_z": 0.4374999893243109, "ce": 6.117925643920898, "genuineness": 4.65797233581543, "identity": 0.7168654203414917, "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_Relief/b8bda3818a30ee8fb30a6aa373934ebd9190c0b51a6b40c653fbfd5809215275.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "b8c4a6cfbe59703a0e0a25a176ba196474bb92bd25f9878bf46502363a3d2583", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "09156757dffde6f6a8765890b7597671f40552b27dd5a37bdfa0d3bd793accde", "generation_seconds_batch": 15.793477678089403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.182358741760254, "target_z": 1.164062538699373, "ce": 6.300607204437256, "genuineness": 4.331617832183838, "identity": 0.6019531488418579, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b8c4a6cfbe59703a0e0a25a176ba196474bb92bd25f9878bf46502363a3d2583.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "b944abf239c00514d5201a8aa0c035247e8df3ae314f183f995464e5f5743753", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "aca70476e16ea07bef8b6a4ca822c935f683ef6db0937547b12bf14bf5bdc571", "generation_seconds_batch": 24.257414555060677, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38699623942375183, "target_z": 0.024414062666807644, "ce": 6.332377910614014, "genuineness": 4.65797233581543, "identity": 0.44847041368484497, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b944abf239c00514d5201a8aa0c035247e8df3ae314f183f995464e5f5743753.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "b96ff65c43cb0faa7ac8cfb8ca905d483ccec8666e577185e4ffd7a24fd88d1f", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "00cfc234604d1281b5cce377c1b85ee31750e1208ae5300adee5bfa2db944a7d", "generation_seconds_batch": 18.585352052934468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.29771390557289124, "target_z": -0.10351562399915415, "ce": 6.1894097328186035, "genuineness": 4.369274139404297, "identity": 0.6848957538604736, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b96ff65c43cb0faa7ac8cfb8ca905d483ccec8666e577185e4ffd7a24fd88d1f.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "b981ab68cae2bd74b4b3fc73b786bd9de03f00eb4cd6f47172d4e737b0dae6ba", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "71550bb08e4506d78a81b34269b81992156d87be0ac29b1be8d7d47b9ae10c7c", "generation_seconds_batch": 25.639295003958978, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9293315410614014, "target_z": 2.234375018682456, "ce": 5.871703147888184, "genuineness": 3.9801597595214844, "identity": 0.4637547433376312, "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_Relief/b981ab68cae2bd74b4b3fc73b786bd9de03f00eb4cd6f47172d4e737b0dae6ba.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "b99a36f0f60c6f17391fb7bc9454b9c5abad1305f0ac812980661aa1c4fde16f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "8bc68e5a1a07962e8e9d2e547d1d4924f531b2cca5296b83715138466dd88b18", "generation_seconds_batch": 25.129970162990503, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44629061222076416, "target_z": 0.10937499733107772, "ce": 6.340320587158203, "genuineness": 4.557555198669434, "identity": 0.7300206422805786, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b99a36f0f60c6f17391fb7bc9454b9c5abad1305f0ac812980661aa1c4fde16f.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "b9c0bc9e5d3b434c25ca78286f64331cc1af14934b1f96ef663d66ff3506b0de", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "92031688db9183c53cf9695caa06cc0e6e3d09b3db9113af6c7abde1555f294d", "generation_seconds_batch": 24.407364869024605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7052775621414185, "target_z": 0.4804687840287591, "ce": 6.483288764953613, "genuineness": 4.268857479095459, "identity": 0.6163827776908875, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b9c0bc9e5d3b434c25ca78286f64331cc1af14934b1f96ef663d66ff3506b0de.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "b9fb70e993101c39ebc8f9de3d7961a96a4815b173007420ead7ddf213ddbc31", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c796b698646091bcedd9edc029eff3ab2be97e75d18d6e8f1d9c81394d7b860b", "generation_seconds_batch": 22.415161711047404, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2926023304462433, "target_z": -0.11083982998836947, "ce": 6.078212261199951, "genuineness": 4.425758361816406, "identity": 0.23495042324066162, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/b9fb70e993101c39ebc8f9de3d7961a96a4815b173007420ead7ddf213ddbc31.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "ba556583e73fc5e522057adcd93b273c7f391b63bc6d94d9cc134d913b625332", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "6f92a2ec50501295efc6c68c4b167cf0b86616afd2d31141953d309f10fbc839", "generation_seconds_batch": 28.299006946966983, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5158081650733948, "target_z": 0.208984386676535, "ce": 5.998785495758057, "genuineness": 4.137060642242432, "identity": 0.6505120992660522, "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_Relief/ba556583e73fc5e522057adcd93b273c7f391b63bc6d94d9cc134d913b625332.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "0c00a0b09d0341e5b3abee4033d12bfe682acc797762144ba93377f3dd35bf8a", "generation_seconds_batch": 18.73381980904378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3406512141227722, "target_z": -0.04199218266257836, "ce": 6.117925643920898, "genuineness": 4.507347106933594, "identity": 0.586767315864563, "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_Relief/ba70e7e208a6b15a9236ccd5a69e0e5fd403df2a937202d690effa2cdc45d9f2.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "bac5e6e36c1473cee46b39455d10454c3a262f81a2e96c01daba0794467a96c8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "d896ceee6c5de6268130a62e6ca78e9a2bab794909f32fb39c28ef5d1873b75a", "generation_seconds_batch": 21.097281535039656, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19616377353668213, "target_z": -0.24902343066088664, "ce": 6.0305562019348145, "genuineness": 4.218649387359619, "identity": 0.4480634927749634, "hypothesis": "Ik heb het kleine doosje gewonden, het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bac5e6e36c1473cee46b39455d10454c3a262f81a2e96c01daba0794467a96c8.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": "bacb9e79d18bd2135034399170ff455e9790778d9b7a5b12f1ae5112de76a930", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ton message est arrivé après mon départ.\n(Natural clear speech.) [3.8 seconds duration] Je l’ai relu... puis j’ai rangé mon téléphone.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand nous pourrons parler.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ba53614043d0c510691683c971f7cb25183afe75f53c62209355e8a9b41ae376", "generation_seconds_batch": 17.383736678981222, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2423346042633057, "target_z": 1.2499999572972436, "ce": 6.149696350097656, "genuineness": 4.507347106933594, "identity": 0.8503624200820923, "hypothesis": "Ton message is arrived after my department telephone. Dimoi Canton.", "wer": 0.9047619047619048, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bacb9e79d18bd2135034399170ff455e9790778d9b7a5b12f1ae5112de76a930.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "bb306a90226b0711a22c24de8aa6a1a0155884b3fb13bd52cb0c3ecaa7cd70e7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "38a1b28183f036008c76ab13849a07cf38458d5dfea57715367bf8e209b1cc15", "generation_seconds_batch": 24.20875903603155, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8770267367362976, "target_z": 0.7265624639695492, "ce": 6.141753673553467, "genuineness": 4.331617832183838, "identity": 0.6458829641342163, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bb306a90226b0711a22c24de8aa6a1a0155884b3fb13bd52cb0c3ecaa7cd70e7.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "bb6d748640711a4ba30caaf2329f6af9ac0a10583eb471203b0206b0998d6c93", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "06d843537f2532cd838aeb970355ca2a0554c3792b0107a6b754b543a5850638", "generation_seconds_batch": 17.78302770096343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19002987444400787, "target_z": -0.257812490658772, "ce": 6.117925643920898, "genuineness": 4.250029563903809, "identity": 0.430625319480896, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bb6d748640711a4ba30caaf2329f6af9ac0a10583eb471203b0206b0998d6c93.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "bb8a9f901903f4dcca7985cd87efee351107f167cfa7bb74e4382f8ca87e280d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "610a4b5cacf464c51c39ada951726829a3df741b12663fdcbaf3811dcf752cda", "generation_seconds_batch": 24.253472791053355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1223828792572021, "target_z": 1.0781251201015027, "ce": 6.173524379730225, "genuineness": 4.457139015197754, "identity": 0.6993396282196045, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bb8a9f901903f4dcca7985cd87efee351107f167cfa7bb74e4382f8ca87e280d.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "bbd4390d5c6e3f6a079de75575118cc8bdb92651665b9189893b6a5d1ca77a31", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ee8624f396ea09d7576778a765ad0d2fd78563110dd1c36f9a02dfd37b8c5633", "generation_seconds_batch": 23.588919047964737, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8688482046127319, "target_z": 0.7148437173057021, "ce": 6.022613525390625, "genuineness": 4.162164688110352, "identity": 0.5173970460891724, "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_Relief/bbd4390d5c6e3f6a079de75575118cc8bdb92651665b9189893b6a5d1ca77a31.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "bbfd7979897bee80c928c667897eb84f27d2adcc4a5fb743c8b06b276524419a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "4ffd00136a674d8ad6bbdb4cef9ccc51eb7c28f81a7aa28b61b6d36bcf809beb", "generation_seconds_batch": 16.24264996103011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7011882662773132, "target_z": 0.474609367994079, "ce": 6.125868320465088, "genuineness": 3.9173994064331055, "identity": 0.33481475710868835, "hypothesis": "The 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_Relief/bbfd7979897bee80c928c667897eb84f27d2adcc4a5fb743c8b06b276524419a.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "bc175ce93e4bec0546c6172653a7b0e08250087e49ce31f41bea802676bdeaa8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d214a6895caa37279766c60ce4d3a3cc43c98b25811e511eeea7dff1a413a6c7", "generation_seconds_batch": 24.57277860294562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.607642412185669, "target_z": 1.7734373652194246, "ce": 5.95112943649292, "genuineness": 4.017816066741943, "identity": 0.4440496563911438, "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_Relief/bc175ce93e4bec0546c6172653a7b0e08250087e49ce31f41bea802676bdeaa8.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "bc34cce85b92d76a56e49987cff61270461b54788e9b541a672d1d6039a5b8a0", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2af23d8a03538a26b2e25875aa8def7823f178e4c44e6495fe97899fde83fa63", "generation_seconds_batch": 26.132411172031425, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1136968731880188, "target_z": -0.367187509341228, "ce": 6.149696350097656, "genuineness": 4.143336772918701, "identity": 0.6629645228385925, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bc34cce85b92d76a56e49987cff61270461b54788e9b541a672d1d6039a5b8a0.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "bc465b521d3a3b96faff59ae5bc798c59f9df0c92b746cf56afaa612a75336a6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "efaccc0c235cacbdacac1f9df06d09752bd25113f4bb4e7316800a1dedbb7ef9", "generation_seconds_batch": 28.890790439909324, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6021902561187744, "target_z": 1.7656251521285702, "ce": 6.252951145172119, "genuineness": 4.15588903427124, "identity": 0.42445510625839233, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bc465b521d3a3b96faff59ae5bc798c59f9df0c92b746cf56afaa612a75336a6.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "bd1e27c77f2a314eec9006f52a226f593da8e04abe2f0011e1bd27fc04452f4b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "2bee6c414440b70b7faf6300519b0ac2cd800a8c084c33ac64433792374bcf1a", "generation_seconds_batch": 16.422688933089375, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6671110391616821, "target_z": 0.42578124266046374, "ce": 6.38003396987915, "genuineness": 4.118232727050781, "identity": 0.5899881720542908, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bd1e27c77f2a314eec9006f52a226f593da8e04abe2f0011e1bd27fc04452f4b.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "bd20ac9b2e2cda83df61f9db04da956d5042ba95cddaf59fc4b8d6391a3e9e37", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "97599c814700a6826062e6b5f2ca2356ade63ba78e5ceb5e24c703b86d6e22e5", "generation_seconds_batch": 22.555117607000284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8252294063568115, "target_z": 0.652343792035526, "ce": 6.157639026641846, "genuineness": 4.545003414154053, "identity": 0.6214759349822998, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bd20ac9b2e2cda83df61f9db04da956d5042ba95cddaf59fc4b8d6391a3e9e37.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": "bd8ac3c79529ea3fc6c44009d80bbdeb5126139cc2c7b0213b0b6f501319a9d6", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "98b8220b05c7938c2860ac5a2a16fc0b7d5016c81e311b6bb83ba98096a029b9", "generation_seconds_batch": 20.202549600042403, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4646923243999481, "target_z": 0.13574219867611206, "ce": 6.3641486167907715, "genuineness": 4.162164688110352, "identity": 0.49312567710876465, "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_Relief/bd8ac3c79529ea3fc6c44009d80bbdeb5126139cc2c7b0213b0b6f501319a9d6.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "be3bccde18fa20219f2da7b49463c3a7551f0cb4a820f8cc662009e371932cd0", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ced9e1d20614536aa4585492be2432a83a4dc79e9d40bfd017ca71e45c11f1d5", "generation_seconds_batch": 20.523833681014366, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9124670624732971, "target_z": 0.7773437279813912, "ce": 6.2767791748046875, "genuineness": 4.432034492492676, "identity": 0.5548929572105408, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/be3bccde18fa20219f2da7b49463c3a7551f0cb4a820f8cc662009e371932cd0.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "be7efcc0ae653002a06b53adbf5f96b2870ca5ecfcd6f98d300db33e6183b08d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b24609796daf7ea76e2ecd33b4cb163153268e2038eceb69f61d8b02d217f72e", "generation_seconds_batch": 26.389304140000604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8529984951019287, "target_z": 2.124999935945865, "ce": 6.300607204437256, "genuineness": 4.394378662109375, "identity": 0.2721562683582306, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/be7efcc0ae653002a06b53adbf5f96b2870ca5ecfcd6f98d300db33e6183b08d.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "bec9d02c2ad0252dcd4c91b5324392103ff8f8fb1dd575a6990590885669d029", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "fc71ce2e1ecc044b319ffd3950067db52e09f1344b2fc4a8848403c627bd5e5c", "generation_seconds_batch": 22.839216521009803, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7984750270843506, "target_z": 2.0468750720609017, "ce": 6.038498878479004, "genuineness": 4.469690799713135, "identity": 0.7724762558937073, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We want regarding.", "wer": 0.3684210526315789, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bec9d02c2ad0252dcd4c91b5324392103ff8f8fb1dd575a6990590885669d029.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": "bedd3a35bae5873dc36641f17105b5def85c6e7f8ef84cb66522713882566714", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "15a1999de27dcefcc7b53a2e09391c9be98534cd03f27337839bd974fa7c5ba3", "generation_seconds_batch": 25.435752124991268, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5498853921890259, "target_z": 0.25781251201015026, "ce": 6.419747352600098, "genuineness": 4.375550270080566, "identity": 0.41126951575279236, "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_Relief/bedd3a35bae5873dc36641f17105b5def85c6e7f8ef84cb66522713882566714.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": "bf1866bc5deeed932afb91f18d512b3dc8a7c0c9b4ccfb564d6ab65610036397", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "45ce40ed8011ee5b4b424c297a9a31848b5cbe9e6b940ef4dd6573905143f547", "generation_seconds_batch": 25.39212818793021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7461702227592468, "target_z": 0.5390625173479948, "ce": 6.213237762451172, "genuineness": 4.7332844734191895, "identity": 0.5771186351776123, "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_Relief/bf1866bc5deeed932afb91f18d512b3dc8a7c0c9b4ccfb564d6ab65610036397.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "bf18d96e04005c26f0b008f646d148fe1556a9cf39e4dd9c73a2b795634ed74d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "bb6d822ed56230986f789230859588780a2ef54c559726943c52e61f7b8a6e1d", "generation_seconds_batch": 26.389304140000604, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8857126235961914, "target_z": 2.171874922601254, "ce": 6.221180438995361, "genuineness": 4.337893962860107, "identity": 0.2482687532901764, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bf18d96e04005c26f0b008f646d148fe1556a9cf39e4dd9c73a2b795634ed74d.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": "bf8ba76e877ccd871a31593eb2ccd1e9bd291f9f92625d102d41de92618e858b", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "53d9357a575d3f29beebae52fce3ecb4baf2ce15ba199850eae664b5f091a006", "generation_seconds_batch": 23.105727571062744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31066325306892395, "target_z": -0.08496093466427007, "ce": 6.062326908111572, "genuineness": 4.406930446624756, "identity": 0.6548627614974976, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle est ici, près de la grand bibliothèque. Nous la remettrons après le déjeuner.", "wer": 0.09523809523809523, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bf8ba76e877ccd871a31593eb2ccd1e9bd291f9f92625d102d41de92618e858b.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "bf97452772809cb8845ada55f6db883a34009f1253edd86a57934de4091a007f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "96bb1006c875334125165f97a72af24130be30c90e50a52dc8d71d578bb9d26b", "generation_seconds_batch": 23.15395933703985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5328467488288879, "target_z": 0.2333984066405861, "ce": 6.308549880981445, "genuineness": 4.381826400756836, "identity": 0.4598652720451355, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bf97452772809cb8845ada55f6db883a34009f1253edd86a57934de4091a007f.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "bfa5e14672368011efd0f69c87645d59956997a0320bcc77850e9f1ee2de8898", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "c8c6e702f43692ceb6cf05c162b40aa1db1f6270eff91c463946983a5833ce3b", "generation_seconds_batch": 16.920473699923605, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27726757526397705, "target_z": -0.13281249065877201, "ce": 6.229123115539551, "genuineness": 4.406930446624756, "identity": 0.6965200901031494, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bfa5e14672368011efd0f69c87645d59956997a0320bcc77850e9f1ee2de8898.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "bfe46a66fe765a0f3945f09618139ba4c69b236e864d22fea7819bf62d48f2da", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4fe0cfde55073028190c6ffedb2e96b0311ab44426c4b5eb4dea69ff452fbf2c", "generation_seconds_batch": 24.30738679692149, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5531189441680908, "target_z": 1.6953125013344612, "ce": 6.221180438995361, "genuineness": 3.998987913131714, "identity": 0.5786373019218445, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/bfe46a66fe765a0f3945f09618139ba4c69b236e864d22fea7819bf62d48f2da.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": "c036aa5dbccdd3fee91c7b1d9be1b8f37eb915452898f69e0ee8e8def716c7e6", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71efe5a7a15b1d2c6d2f4db19403ea8e0a8025073f8a6fcde81dcf9f9e1dad0d", "generation_seconds_batch": 21.267526806914248, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.838860273361206, "target_z": 0.6718750080067668, "ce": 6.316492557525635, "genuineness": 4.356721878051758, "identity": 0.6784559488296509, "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_Relief/c036aa5dbccdd3fee91c7b1d9be1b8f37eb915452898f69e0ee8e8def716c7e6.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "c04c7f28d1a3cb9c25be4a166436987be94f796d1ef5e15076893d14c725c218", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "ecc2c2cbd47a7bc7eb2cdd6872f907ef86c0cc7859d9785dbef6322be5bd4ec8", "generation_seconds_batch": 24.85255292407237, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.765760898590088, "target_z": 2.000000085405513, "ce": 6.022613525390625, "genuineness": 3.986435890197754, "identity": 0.433565616607666, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay.", "wer": 0.058823529411764705, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c04c7f28d1a3cb9c25be4a166436987be94f796d1ef5e15076893d14c725c218.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "c09035f0e04125d00fc8388b5d5f470379514cad04206d87da9a34deb344dbc8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "88c041c84910c811a5cab700d2d7f5e3ab04cab929f59c6ea20fa94cb8c53203", "generation_seconds_batch": 24.049309851950966, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1441922187805176, "target_z": 1.1093749973310778, "ce": 6.252951145172119, "genuineness": 4.143336772918701, "identity": 0.6020606160163879, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c09035f0e04125d00fc8388b5d5f470379514cad04206d87da9a34deb344dbc8.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "c090f4c1c6c083396bcda55f0675bc8a253f43c00b359cb9e44a9aa40fd79ff7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f92be2cc5279f316cb646c3b0d4b1a586c07941e05772f54a23b690fdba71857", "generation_seconds_batch": 15.789189751958475, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3350247144699097, "target_z": 1.3828125333615287, "ce": 6.0305562019348145, "genuineness": 4.162164688110352, "identity": 0.5538188219070435, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c090f4c1c6c083396bcda55f0675bc8a253f43c00b359cb9e44a9aa40fd79ff7.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "c13b23e64c055e13c9586899ddef9a33ed6c70832d99aa030d6208205b55cb52", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "cfe028b4378440567e3ccab8f8662d284515b5346e84aa996e06f76ae37065a0", "generation_seconds_batch": 24.57277860294562, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0215141773223877, "target_z": 0.9335937119678575, "ce": 5.998785495758057, "genuineness": 3.810706615447998, "identity": 0.5275081396102905, "hypothesis": "La puerta sigue abierta y he dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.06666666666666667, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c13b23e64c055e13c9586899ddef9a33ed6c70832d99aa030d6208205b55cb52.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "c151c939aead622e62f9c50045fb124c1c3c2a19ab8b0c86404d30e2b1ad9da7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1701, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4a49791c12542bfb314795c4b78bad1644eb98a5cf2cf6d250dd05bfee004426", "generation_seconds_batch": 24.06204975291621, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30146241188049316, "target_z": -0.09814451398540898, "ce": 6.1894097328186035, "genuineness": 4.413206577301025, "identity": 0.4731481969356537, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c151c939aead622e62f9c50045fb124c1c3c2a19ab8b0c86404d30e2b1ad9da7.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "c16556234e89b23a3a599f3f9baaad8d4ab4516ff90be0e56a97eb179582a3e4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fe0d04882e0decf762f3fb2711c38a8a49ea0d7a1a6267929775696a1d36f78f", "generation_seconds_batch": 24.41722085198853, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9806215167045593, "target_z": 0.8749999786486218, "ce": 6.221180438995361, "genuineness": 3.8922953605651855, "identity": 0.26091182231903076, "hypothesis": "The 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_Relief/c16556234e89b23a3a599f3f9baaad8d4ab4516ff90be0e56a97eb179582a3e4.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "c192015ce80bb7ab25d07c7567c24107e11bc366b94dee0947e808b7b1796954", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fc5d7ae0b28defe6eeb469e7a43b82d8bfc130da9ac2b63e1106c3ff28102187", "generation_seconds_batch": 24.928334239986725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6657479405403137, "target_z": 0.423828103982237, "ce": 5.879645347595215, "genuineness": 3.9801597595214844, "identity": 0.6165063977241516, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c192015ce80bb7ab25d07c7567c24107e11bc366b94dee0947e808b7b1796954.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "c1a43fc401e546e7fd77f53aed3219707bb18b14bedc07460bcb7c14b74256b8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a8b041a82131c2ce9710bb997290f7bf95c786ff78d10c36e5b1d80fc5b01690", "generation_seconds_batch": 27.94715218199417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5294390320777893, "target_z": 0.22851560264777587, "ce": 6.268836498260498, "genuineness": 4.381826400756836, "identity": 0.6939095258712769, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c1a43fc401e546e7fd77f53aed3219707bb18b14bedc07460bcb7c14b74256b8.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "c25fe39f97edbb7ea2b94d635e551892fa16df72f7efc80cbdb211bdfb44fd00", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "a80c1f763b970e0ebf0b9d88de1c6649022b59a8c6c184ec4bb558e49f27aa6e", "generation_seconds_batch": 24.25185312097892, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5417068600654602, "target_z": 0.24609376534630312, "ce": 6.308549880981445, "genuineness": 4.13078498840332, "identity": 0.4551158547401428, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c25fe39f97edbb7ea2b94d635e551892fa16df72f7efc80cbdb211bdfb44fd00.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "c2ce7d347b5fcc09086832d50fa95e5435fb5ec4c7cdebf7542b231bc091db2a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "08f135fa685dd36897efb93a0215c29d924015f075ff189feb594a3879365f90", "generation_seconds_batch": 25.54912859702017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0133357048034668, "target_z": 0.9218750507095234, "ce": 5.839932441711426, "genuineness": 3.6977379322052, "identity": 0.63515704870224, "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_Relief/c2ce7d347b5fcc09086832d50fa95e5435fb5ec4c7cdebf7542b231bc091db2a.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "c2e7857bf717fe2547ed0bb3bf3d7ce571f4d693c8a0bab6c53302302cfe04f6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "743b307fcb121f4792224a6ee2144c42dd54c934a920df2dc87d181553e4b1a9", "generation_seconds_batch": 25.67964490898885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8879314661026001, "target_z": 0.7421874879898497, "ce": 6.141753673553467, "genuineness": 4.105680465698242, "identity": 0.35258176922798157, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c2e7857bf717fe2547ed0bb3bf3d7ce571f4d693c8a0bab6c53302302cfe04f6.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "62e5d757369f4809a8cfd1a2b0741428854fcf2bc27d9a182c74fd775ca2789a", "generation_seconds_batch": 16.892100521014072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23160408437252045, "target_z": -0.19824218800042293, "ce": 6.038498878479004, "genuineness": 4.457139015197754, "identity": 0.7580861449241638, "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_Relief/c3977db0634952a7f9e4083e6135fbbc87199d34c7cb8c3338515d9ae38c18f4.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "c468b7dda2189cd1bec74fa2c20625497b2005b6ac13668ab63d4c3afe84b8ba", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "9ba4ce95c5e2d0768391d69319ab333395e3d2af483b0621298bf28dd36516f4", "generation_seconds_batch": 21.483410452958196, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17912515997886658, "target_z": -0.2734374933276943, "ce": 6.1894097328186035, "genuineness": 4.2374773025512695, "identity": 0.712067723274231, "hypothesis": "Ik heb een kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c468b7dda2189cd1bec74fa2c20625497b2005b6ac13668ab63d4c3afe84b8ba.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "3ad7e544c76764852cfd5b7f5fd3e29f963a80a588455264e5e48da0e59828f2", "generation_seconds_batch": 18.456065137987025, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17367279529571533, "target_z": -0.28125000533784456, "ce": 6.157639026641846, "genuineness": 4.369274139404297, "identity": 0.7214454412460327, "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_Relief/c493619abd8899c9b3ce96f2a00a6bcdd900e874ef21436707b986365a8437ee.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "c4db4c92fa20daf9e4e677d4fee7556d20b134d42a667cc3e9c9e39b4eadacaf", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "90fce91a38e9b04a2032a1971f79c5c95f63332f95f70ab5ba4734498eea0143", "generation_seconds_batch": 24.54998477094341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2477869987487793, "target_z": 1.2578125120101502, "ce": 6.395919322967529, "genuineness": 4.432034492492676, "identity": 0.3898199200630188, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c4db4c92fa20daf9e4e677d4fee7556d20b134d42a667cc3e9c9e39b4eadacaf.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "c4ed2ee29daf49e954ef5061c98a092d9c6bd88303808bccb251a18f196cfb9b", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "05e653c9600f42337b57af32e4b5b59c808e1fea60109df3f430a9e3044bf0f5", "generation_seconds_batch": 17.520369679899886, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5040476322174072, "target_z": 1.6249998505403522, "ce": 6.268836498260498, "genuineness": 4.331617832183838, "identity": 0.4162110388278961, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c4ed2ee29daf49e954ef5061c98a092d9c6bd88303808bccb251a18f196cfb9b.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "c4f3d6eb76be9e98aad8860c4941126589b73e2148969303aeb367b34f2d17f7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "14c19e40b7173400676ec6534e38196bbaf93159f2b28940a9c4e28bc04c2b11", "generation_seconds_batch": 25.14602584205568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38733699917793274, "target_z": 0.024902325984986054, "ce": 6.197352409362793, "genuineness": 4.570107460021973, "identity": 0.5709222555160522, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c4f3d6eb76be9e98aad8860c4941126589b73e2148969303aeb367b34f2d17f7.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "c4f5e48a251e65398691bc3e05c0707735449ca12aae811c04b580370a4aab53", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "a44ca4247787e41e8d26257ee16b46140c5f0530f081e82f698f9eba8af17051", "generation_seconds_batch": 30.356426057987846, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6453015804290771, "target_z": 0.39453119461986264, "ce": 6.054384231567383, "genuineness": 4.093128204345703, "identity": 0.6047130823135376, "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_Relief/c4f5e48a251e65398691bc3e05c0707735449ca12aae811c04b580370a4aab53.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "c56122f48c3c4f306707c060da70ac53d9e5e772eacb0718c7b79a482f785858", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 0.75, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6014028e322fde5f66eeef69ef8dd86e17b81b5e20689a031525e73edc758c68", "generation_seconds_batch": 26.62664995295927, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09325054287910461, "target_z": -0.39648437600084585, "ce": 5.982900142669678, "genuineness": 4.293961524963379, "identity": 0.6160532236099243, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c56122f48c3c4f306707c060da70ac53d9e5e772eacb0718c7b79a482f785858.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "c58470fdbc6fe1363a9667831dcd3271701cc82ccb350200dc1a0eea48e69792", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 1.0, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f2e9031312b242d0bf509e2cd416de1fcfd08159f5423839e92771d5e166b128", "generation_seconds_batch": 24.928334239986725, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5880519151687622, "target_z": 0.31250005337844566, "ce": 6.252951145172119, "genuineness": 4.319066047668457, "identity": 0.8201144933700562, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis moi quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c58470fdbc6fe1363a9667831dcd3271701cc82ccb350200dc1a0eea48e69792.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "c59216624f355433c4df042fc976d7be9eca4072d065cc9147c634b87af07ef1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "cfee5b0f7c57242c00e119ea839c36e996ff26a9046554ed0a2c51cd39ba3b42", "generation_seconds_batch": 31.657955243019387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8497649431228638, "target_z": 0.6874999466215543, "ce": 6.324435234069824, "genuineness": 3.886019229888916, "identity": 0.16474109888076782, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c59216624f355433c4df042fc976d7be9eca4072d065cc9147c634b87af07ef1.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "c5c74320c43371ede8ac1c47045a5b09bf7ede0c4ad72763a3ff66fd5abaf17e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "55e037022f3b40aea94d713dfaa605cd9536f7f812befb237e86e09ce741dc8a", "generation_seconds_batch": 15.512249491992407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6602956056594849, "target_z": 0.41601563467484326, "ce": 6.23706579208374, "genuineness": 4.080576419830322, "identity": 0.3381803631782532, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c5c74320c43371ede8ac1c47045a5b09bf7ede0c4ad72763a3ff66fd5abaf17e.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "c61ad60eb9d8fdafc6aaec1b0dd5c9f5456db797275a0f04152c551965edbbfc", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "379c77aef2a457ff56e69103d3c9133da967a6502326479a2d4f305dd8e57153", "generation_seconds_batch": 24.889950006036088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.430615097284317, "target_z": 0.08691407334249678, "ce": 6.340320587158203, "genuineness": 4.632867813110352, "identity": 0.2777060866355896, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c61ad60eb9d8fdafc6aaec1b0dd5c9f5456db797275a0f04152c551965edbbfc.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "c786daad5edea0f8a3285f004969d0a15275262c1261b200d4dc51b9279d9ba7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "b2da0adb2a5b13d8e7c414e0c27d6a387715d334c2051836c99bd3e3c28fb886", "generation_seconds_batch": 25.296027738018893, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3404769897460938, "target_z": 1.3906249172634093, "ce": 6.300607204437256, "genuineness": 4.519899368286133, "identity": 0.37998154759407043, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c786daad5edea0f8a3285f004969d0a15275262c1261b200d4dc51b9279d9ba7.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "c7a94cb192eb73c60be75a2ab968c2883770b08f55f25bc71bd45ddef51cfb45", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "0e719ae980bf14a6f8f2c7399805b058df188b5439de4386676ccbec91dee5e1", "generation_seconds_batch": 16.22829673695378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2859535217285156, "target_z": 1.3125000533784457, "ce": 6.268836498260498, "genuineness": 4.262581825256348, "identity": 0.3399256467819214, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c7a94cb192eb73c60be75a2ab968c2883770b08f55f25bc71bd45ddef51cfb45.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "37b564b5b40e0161255deba594c08ff8cc735272243f53479a5eaeb0c0348fc2", "generation_seconds_batch": 19.990200657979585, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24182724952697754, "target_z": -0.183593754670614, "ce": 6.23706579208374, "genuineness": 4.381826400756836, "identity": 0.6734955310821533, "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_Relief/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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "05763f5575e9d5c43b6e0dcc5b8fc2d444fc59f3c5aadd9bd376909a61b8cc0a", "generation_seconds_batch": 16.897238890989684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24319034814834595, "target_z": -0.1816406159923873, "ce": 6.38003396987915, "genuineness": 4.406930446624756, "identity": 0.4807514548301697, "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_Relief/c8907269f81c0a33f09ba3b9d9f76b6acb2a8250e6881dbc11786cea01719e9d.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "c91acf0e618072e57e13bebadef3e274365eb093daf07d951206236d122f925d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e97aa73f518991a07d247ea46673944db99a942caaa1971571acc8bd75c07118", "generation_seconds_batch": 22.555117607000284, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4200511574745178, "target_z": 0.07177735534313116, "ce": 6.078212261199951, "genuineness": 4.6705241203308105, "identity": 0.5934381484985352, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi, quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c91acf0e618072e57e13bebadef3e274365eb093daf07d951206236d122f925d.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "c92eabb3588f9a3f15c0a9cb3c69d18f27e6086d11ecca3a0bf88550af293199", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8d3a3611438e859f19b0d77fd06635c04742abd674d9ba8477d4e3ae35f91a85", "generation_seconds_batch": 18.492925032041967, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.7275943756103516, "target_z": 1.9453125440372177, "ce": 6.086154937744141, "genuineness": 4.3881025314331055, "identity": 0.74311363697052, "hypothesis": "I thought the pet. It was pretty lay fenêtre. We got.", "wer": 0.9473684210526315, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/c92eabb3588f9a3f15c0a9cb3c69d18f27e6086d11ecca3a0bf88550af293199.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": "ca22f1a9448253f2d2efefa6dc990dab452172b618c1b9aa187b966609fd8c6a", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "fe77c1123be7b059e4b356bbf2da73c110a9a77c37bd29f5b34c45570d400427", "generation_seconds_batch": 17.433295511989854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7952414155006409, "target_z": 0.6093749973310777, "ce": 5.824047088623047, "genuineness": 4.325342178344727, "identity": 0.71849524974823, "hypothesis": "J'ai écrit le numéro sur l'enveloppe, lis les biens 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_Relief/ca22f1a9448253f2d2efefa6dc990dab452172b618c1b9aa187b966609fd8c6a.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "cadd3e0af317d69fc683b17aa090b0b5e4197036d48379c3186c70e4a006cd12", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8f0dd5effe7e0fbe032f1017f3b6467ae43b8f084d2e653a50406fb69b5fc144", "generation_seconds_batch": 18.192228564992547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48036783933639526, "target_z": 0.158203122664693, "ce": 6.348263263702393, "genuineness": 4.6705241203308105, "identity": 0.592327356338501, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/cadd3e0af317d69fc683b17aa090b0b5e4197036d48379c3186c70e4a006cd12.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "cb6b3d97da2e72973faeefce03165b4d23a1e0dc427be1d5f37c0767522b7501", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "264b3fb6af2d5ca8541f513fe4ac3c9cf3c37929025ea2d3714bb259037d491f", "generation_seconds_batch": 16.463791732909158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2423346042633057, "target_z": 1.2499999572972436, "ce": 5.847874641418457, "genuineness": 3.9801597595214844, "identity": 0.4687879681587219, "hypothesis": "La puerta sigue abierta. He dejado tu abrijo sobre la silla. Dime cuándo estás lista.", "wer": 0.13333333333333333, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/cb6b3d97da2e72973faeefce03165b4d23a1e0dc427be1d5f37c0767522b7501.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "cb7b3f711386697c1d58fdec433d705a44bebfc6c92e41de893b7949f2ee5a0d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "16c30e4919c74a39fabe0837b38a593620f88102a013a69cdc2419ec3b9a0ed1", "generation_seconds_batch": 18.199155142065138, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20638693869113922, "target_z": -0.23437499733107772, "ce": 6.149696350097656, "genuineness": 4.18099308013916, "identity": 0.6142157912254333, "hypothesis": "Ik 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_Relief/cb7b3f711386697c1d58fdec433d705a44bebfc6c92e41de893b7949f2ee5a0d.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "cc128bb0ac185e89477c6d01d6d2166cb4bcb4fe7807032bbd8bb775f5cba975", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "009b33df9d5f3612386481545e0392a99f5b0c94a443d0a279c677fef4f563e1", "generation_seconds_batch": 27.33497404505033, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5585713386535645, "target_z": 1.7031250560473679, "ce": 6.213237762451172, "genuineness": 4.582659721374512, "identity": 0.5387909412384033, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre.", "wer": 0.3684210526315789, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/cc128bb0ac185e89477c6d01d6d2166cb4bcb4fe7807032bbd8bb775f5cba975.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": "ccb8c73f6f9727209a0466fe9a83d01b504c45cbb80bb3324c6ed11f949621c1", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d1f119b34f85b0e1d1abbc9ff19c0a830ec71f3e5adde1820421925b2b46ab9b", "generation_seconds_batch": 18.615383217926137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.339969664812088, "target_z": -0.042968752001691715, "ce": 6.260893821716309, "genuineness": 4.469690799713135, "identity": 0.6168299913406372, "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_Relief/ccb8c73f6f9727209a0466fe9a83d01b504c45cbb80bb3324c6ed11f949621c1.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "cd012e32f05602699cf6af988ea045bdbcb9f29b1f376b6d1cbe9e1229212298", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "fe6f6adb5202aab61a4064e4b4e4fd9aabfc126dfa81e1738644d3410da74f0e", "generation_seconds_batch": 18.501691431971267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43538588285446167, "target_z": 0.09374997331077717, "ce": 6.268836498260498, "genuineness": 4.519899368286133, "identity": 0.6893589496612549, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/cd012e32f05602699cf6af988ea045bdbcb9f29b1f376b6d1cbe9e1229212298.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "ce029c368f9c020153b58df84600acf154e62a719b776e5e7f2814190bd5ee55", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cc53d926d2b93d2094c97eed518abdf960fb147149b10015f4ee40316b14b6a3", "generation_seconds_batch": 18.60131783701945, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17639897763729095, "target_z": -0.27734374933276945, "ce": 6.109982967376709, "genuineness": 4.18099308013916, "identity": 0.661684513092041, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ce029c368f9c020153b58df84600acf154e62a719b776e5e7f2814190bd5ee55.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "ce503bb7b421953c8a6e653f731e363321e77443330d617eab3dd33f3581ab29", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "5454ab2101f32d9947252bc6f206f4d9cadced0b2b9351fac85a76ddec077696", "generation_seconds_batch": 23.192078102962114, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.166001558303833, "target_z": 1.1406248745606526, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.2096148431301117, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ce503bb7b421953c8a6e653f731e363321e77443330d617eab3dd33f3581ab29.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": "ce71b19abb2d5573893e181e2ee37251e18ab1fb833ce55125760ccd1ffa4877", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "6068ba63767dacbe9d79ded21faae9a1e890399afcdcd6053efa31b135836777", "generation_seconds_batch": 18.399398664943874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.608498215675354, "target_z": 0.341796877335307, "ce": 6.23706579208374, "genuineness": 3.9927117824554443, "identity": 0.5963211059570312, "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_Relief/ce71b19abb2d5573893e181e2ee37251e18ab1fb833ce55125760ccd1ffa4877.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "cecd6d0145724cbfe96520ba73d9e974e31ee0a8d60ab7466c4471055eef01fe", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "f9cae270c94d85eb2c22578fea82ec862652e03a912fd1f3c22ec11b8f3a1f68", "generation_seconds_batch": 25.63570612797048, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2830606997013092, "target_z": -0.12451171533044332, "ce": 6.157639026641846, "genuineness": 4.557555198669434, "identity": 0.5168343782424927, "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_Relief/cecd6d0145724cbfe96520ba73d9e974e31ee0a8d60ab7466c4471055eef01fe.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "9b08637ce2cd30a827328755cb23c705cb845f08006daacbc67758b04379a4e6", "generation_seconds_batch": 16.89595431298949, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14095866680145264, "target_z": -0.32812499199323314, "ce": 6.316492557525635, "genuineness": 4.381826400756836, "identity": 0.5916049480438232, "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_Relief/cf68e6506caaaad7e7371e72de9d5417fef89211300487ff83acd2484eaab510.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "cf73e3b5b293ba02903c7f40c054dd5da9a7267ff5e79b9235ee40649d0c3723", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 129, "seconds_generated": 10.32, "mp3_sha256": "5e03a27645062976e12de3440bf5c2ec5efcfe613c5902c7a92502b414dacaa0", "generation_seconds_batch": 23.088593100081198, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3731911182403564, "target_z": 1.437499903918798, "ce": 6.0305562019348145, "genuineness": 4.262581825256348, "identity": 0.4300846457481384, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que.", "wer": 0.11764705882352941, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/cf73e3b5b293ba02903c7f40c054dd5da9a7267ff5e79b9235ee40649d0c3723.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "d02dc5b0975a2c333f6ab66f420b545c264c7cef0032c064739cb8c5def9cfa0", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "d454c64d4ff20ca31e07dbb36c952d7c1dce9c74051b2dbc1f4c380391b530ae", "generation_seconds_batch": 25.190532780019566, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45787686109542847, "target_z": 0.12597654798773508, "ce": 6.197352409362793, "genuineness": 4.469690799713135, "identity": 0.48363882303237915, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d02dc5b0975a2c333f6ab66f420b545c264c7cef0032c064739cb8c5def9cfa0.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "d0b79b1a44eec9727bd1a33c5e11ccb5f4f95bb9bc6b25673d0a47ab0fb2ebb5", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "1fe8b035535a77a4646e30e5e0125c9dad389a20215d9854763997212138b8d4", "generation_seconds_batch": 18.49221270403359, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2159285545349121, "target_z": -0.22070313334038213, "ce": 6.141753673553467, "genuineness": 4.231201171875, "identity": 0.656063973903656, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d0b79b1a44eec9727bd1a33c5e11ccb5f4f95bb9bc6b25673d0a47ab0fb2ebb5.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "18ef41d623efa4a2f70c46d36a41d310711bd6fcdb49e0e595f74c05ead2fb25", "generation_seconds_batch": 18.357007098034956, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2622735798358917, "target_z": -0.15429688801099614, "ce": 6.348263263702393, "genuineness": 4.218649387359619, "identity": 0.5696573257446289, "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_Relief/d11caac31fa3732e2517803823f1b039213fb31e9438619fd83d8b232c894b7d.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "d12c79b9b65264f5464a1b97b00d0a26decceabd6b1234ff30e795c9ce8abc07", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "375c507ccc10499799fafd377fc39b703a7f1ff8a4364474bb5d3d3a8bc81ee6", "generation_seconds_batch": 22.44120661902707, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.30998170375823975, "target_z": -0.08593750400338343, "ce": 6.221180438995361, "genuineness": 4.7081804275512695, "identity": 0.42837226390838623, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d12c79b9b65264f5464a1b97b00d0a26decceabd6b1234ff30e795c9ce8abc07.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": "d212ec8b8f924bcba6fff0a95e28c889b137ac860f55c2ebd26c2c050af367e2", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] La colocaremos después de comer.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Alguien ha movido la pequeña silla azul.\n(Natural clear speech.) [3.8 seconds duration] Estaba aquí... junto a la estantería alta.\n(Natural clear speech.) [3.2 seconds duration] La colocaremos después de comer.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "e5e13b3f4f515d0f1c9abadeccff0d803958c61ef3464ba475872aaa405aa31e", "generation_seconds_batch": 19.82387769804336, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.542388379573822, "target_z": 0.24707029198265995, "ce": 6.213237762451172, "genuineness": 4.607763767242432, "identity": 0.5721389055252075, "hypothesis": "Alguien ha movido la pequeña silla azul. Estaba aquí junto a la estantería alta. La colocaremos después de la casa.", "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_Relief/d212ec8b8f924bcba6fff0a95e28c889b137ac860f55c2ebd26c2c050af367e2.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "347691a4c968a34866fab62ce13bb16cf2af6f1dddab13d8454b3e6e5f1ff645", "generation_seconds_batch": 15.993275003042072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2834014594554901, "target_z": -0.12402345201226492, "ce": 6.157639026641846, "genuineness": 4.6705241203308105, "identity": 0.6537876725196838, "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_Relief/d2319f0ba4d4a13f099c61fd2524d2cd47bb09bca092815ed8a29e7f5b0c527c.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "d247a32d8e3bf2ce5aaf72dd5d8e27532dc222a7d58e27f5865536056d459145", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0f2e5b1060009f976fd6976bd99d1259ab84ee5aec4786878520e9c59da70c74", "generation_seconds_batch": 19.919616841012612, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2377379834651947, "target_z": -0.18945312800253758, "ce": 6.324435234069824, "genuineness": 4.519899368286133, "identity": 0.6867763996124268, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d247a32d8e3bf2ce5aaf72dd5d8e27532dc222a7d58e27f5865536056d459145.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": "d272974a96b68620a90d774814b01550d106fdb2cc81852112f7b96adffb0b69", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Natural clear speech.) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Natural clear speech.) [3.2 seconds duration] Bel me wanneer je even tijd hebt.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "81710b5d675525cdca6f6fdf84a3f048c2b54364b74cd3c628b74153b9c4e4c9", "generation_seconds_batch": 20.19425267796032, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18457750976085663, "target_z": -0.2656250026689223, "ce": 6.046441555023193, "genuineness": 4.268857479095459, "identity": 0.7396952509880066, "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_Relief/d272974a96b68620a90d774814b01550d106fdb2cc81852112f7b96adffb0b69.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "d2d01a512f0656197bbfc4b9b3ba93e9312f999f3b5acf15cd3c7f8328796f6c", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "69bbc6ccff59e04fa089db09878b3a6d9ae6bf56d8bcce49be8244ac30da5410", "generation_seconds_batch": 21.52875512908213, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.10824453830718994, "target_z": -0.3749999786486217, "ce": 6.213237762451172, "genuineness": 4.419482707977295, "identity": 0.45713040232658386, "hypothesis": "De deur staat nog open. Ik heb je jas op de deur staat nog open. Ik heb je jas op de stoel gelegd.", "wer": 0.5789473684210527, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d2d01a512f0656197bbfc4b9b3ba93e9312f999f3b5acf15cd3c7f8328796f6c.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "d2de0cd478337895760b7f4c73dd33cfe33261abdd8976cd12118fd7d2bea2e4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "8429196b59ca5aa3a609fe78db8793267713656353480d5cd88a4b67de72226d", "generation_seconds_batch": 26.94112716394011, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6398493051528931, "target_z": 0.3867188107179819, "ce": 6.38797664642334, "genuineness": 4.15588903427124, "identity": 0.41805848479270935, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d2de0cd478337895760b7f4c73dd33cfe33261abdd8976cd12118fd7d2bea2e4.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "d2df19a7e434145c2dc49b420215a0cf3247ed0624dd6598c7996d0e35d0f73e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "c2b10ba70942f87ff709df30c6161123881790dea15d8102e7bff766d43b7c9f", "generation_seconds_batch": 24.745249446015805, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7148191928863525, "target_z": 0.49414066937083295, "ce": 6.419747352600098, "genuineness": 4.337893962860107, "identity": 0.5027751326560974, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d2df19a7e434145c2dc49b420215a0cf3247ed0624dd6598c7996d0e35d0f73e.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "d2e74d392cebb23b886998e156d1bf5d0cae49309c347b54f99ef3da73076efe", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9801e1666c7043deee37675e4485b8adebd457e6b99e7e74efd104f3c04f35b8", "generation_seconds_batch": 16.463791732909158, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0133357048034668, "target_z": 0.9218750507095234, "ce": 5.95112943649292, "genuineness": 3.8044304847717285, "identity": 0.5466866493225098, "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_Relief/d2e74d392cebb23b886998e156d1bf5d0cae49309c347b54f99ef3da73076efe.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "d2e8dd24a35cd9e119ea535b6f59ecbd9f872227acb160b28ef1c39d6e62aa99", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f97323213798b300b7e1ce1658cc3b14e829fbe748ab603e5e3f239f688283e5", "generation_seconds_batch": 24.75534830603283, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6294519901275635, "target_z": 1.804687584071052, "ce": 6.125868320465088, "genuineness": 4.256305694580078, "identity": 0.5968946218490601, "hypothesis": "Te he encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.058823529411764705, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d2e8dd24a35cd9e119ea535b6f59ecbd9f872227acb160b28ef1c39d6e62aa99.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "d380cd58e03ba6613d544d5bd31601cc85df127ab845be5e82d2c8ba6ee2a662", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "f4880142979c41fdde98e4a6b8c177f5f8218df8273edacd6a31c4561f1ddf34", "generation_seconds_batch": 22.699557490996085, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.182358741760254, "target_z": 1.164062538699373, "ce": 6.41180419921875, "genuineness": 4.7332844734191895, "identity": 0.45448988676071167, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d380cd58e03ba6613d544d5bd31601cc85df127ab845be5e82d2c8ba6ee2a662.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "d3e5e4d538da62d7b6591c25e35b7503e0547aac69644b4db6567a7392d8f831", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "dabc0add3362b167f8ac4b35c60b06530eed8fd9560b70a5d4ad5190da32765b", "generation_seconds_batch": 24.898162225959823, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.28646841645240784, "target_z": -0.1196289113376331, "ce": 5.911416053771973, "genuineness": 4.243753433227539, "identity": 0.5264240503311157, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d3e5e4d538da62d7b6591c25e35b7503e0547aac69644b4db6567a7392d8f831.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "f4b19eba78eb4b78bf4f80b4d9ebc38e1d8b8f8f7954d2f33248a813157f6015", "generation_seconds_batch": 16.564378419076093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.48104938864707947, "target_z": 0.15917969200380636, "ce": 5.998785495758057, "genuineness": 4.413206577301025, "identity": 0.7358470559120178, "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_Relief/d3fab0ead1fc9dcf899f59bddb0c9d4b54373ba1829b6dc49f77fc4027ce1740.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "d505d0598c15b756d98067e616f65ccda35e34fe902cf749b23efa0e4c142b29", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "93336f31276aa66ad5c3c94bcee2571e127c016a50c3519e6d8ccfa4d02547d5", "generation_seconds_batch": 21.98693248501513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4824124574661255, "target_z": 0.16113278797927652, "ce": 5.990842819213867, "genuineness": 4.2249250411987305, "identity": 0.6884400844573975, "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_Relief/d505d0598c15b756d98067e616f65ccda35e34fe902cf749b23efa0e4c142b29.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": "d55cf08ecbe3d6c88a78509ecd98ac1779ba519728202512317f3c1d85d79cbb", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Your message arrived after I had left.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Let me know when we can talk.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Your message arrived after I had left.\n(Natural clear speech.) [3.8 seconds duration] I read it twice... before putting the phone away.\n(Natural clear speech.) [3.2 seconds duration] Let me know when we can talk.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f6cb7f9ccf4252a83fe7c0b8881e43794db930c5fc3a48e8d5060803d7423b10", "generation_seconds_batch": 17.637080927030183, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1550970077514648, "target_z": 1.1250001067568913, "ce": 6.372091293334961, "genuineness": 4.2249250411987305, "identity": 0.37703025341033936, "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_Relief/d55cf08ecbe3d6c88a78509ecd98ac1779ba519728202512317f3c1d85d79cbb.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "d5bea26d6c035e08147394011f0eca3b4e06d9276070a1acc3344f0129e2d126", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "360e318540daf6231e0a701ae2d6d0c8a659f756835d638ca93694ecac2be37d", "generation_seconds_batch": 24.15843719500117, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24182724952697754, "target_z": -0.183593754670614, "ce": 6.022613525390625, "genuineness": 4.319066047668457, "identity": 0.6642862558364868, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar, wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d5bea26d6c035e08147394011f0eca3b4e06d9276070a1acc3344f0129e2d126.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "d5c0583ec96c51f59dc3b356f82bccdc7ead6fc7c862fd98be565e02fcf39cce", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "dbfdce85c0b752243455b4a6cea844886e368b5a763f64f112f6c9176bbe8a3f", "generation_seconds_batch": 24.06975228805095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0569545030593872, "target_z": 0.9843749759796995, "ce": 5.593709468841553, "genuineness": 3.961331605911255, "identity": 0.48107239603996277, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos?", "wer": 0.23529411764705882, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d5c0583ec96c51f59dc3b356f82bccdc7ead6fc7c862fd98be565e02fcf39cce.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": "d5d7f5d3a241fbbf966468f00f78b19c1533be66062657bcbf625b77d6db8e0d", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "df638b0467dabc04a30d304e74cb524114cc0d5932c3b27da32593879d04a26a", "generation_seconds_batch": 22.213161524035968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7243608236312866, "target_z": 0.5078125547129068, "ce": 6.197352409362793, "genuineness": 4.432034492492676, "identity": 0.5748827457427979, "hypothesis": "Escribí el número en el sobre, léelo bien y comprueba las dos últimas cifras. Llámame cuando tengas un momento.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d5d7f5d3a241fbbf966468f00f78b19c1533be66062657bcbf625b77d6db8e0d.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": "d5e39db3f39419293ca74abbb49c117ad3d92e8af2c85b8129ed386862ae538c", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "8346c112b559fb25ef1a8f5fa44811fd8c9e5826b5cc487418a94f5811fae733", "generation_seconds_batch": 25.59593162301462, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4275481402873993, "target_z": 0.08251953266786496, "ce": 5.839932441711426, "genuineness": 4.444586753845215, "identity": 0.7498935461044312, "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_Relief/d5e39db3f39419293ca74abbb49c117ad3d92e8af2c85b8129ed386862ae538c.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "d689de09b085205178adbf907037639b9b6d7c983ed96b3c3a5a8b15a61ce221", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "411bb291688f6b1edd2ea5d805fade5402cc11a47dbb0603725f815d62dd792f", "generation_seconds_batch": 22.98299505491741, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.568968653678894, "target_z": 0.285156282694298, "ce": 6.268836498260498, "genuineness": 3.9676074981689453, "identity": 0.2800171673297882, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d689de09b085205178adbf907037639b9b6d7c983ed96b3c3a5a8b15a61ce221.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "d6b99412ada158c452361a16707d55c8ea80c621e2d3ac508a234ff216869704", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "b8ada5ce630e57d97136720737d741bf590763de91601747011d4d1d18fd10a8", "generation_seconds_batch": 23.835226839990355, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9588121175765991, "target_z": 0.8437500160135337, "ce": 6.332377910614014, "genuineness": 4.457139015197754, "identity": 0.7540512084960938, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d6b99412ada158c452361a16707d55c8ea80c621e2d3ac508a234ff216869704.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "d6c955ef1500deb7533c7f9dc970fcb895a7ec5869241ce602e8cd62cdcfdc32", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1702, "scale": 1.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f42ce69b2be833d70388a4731b3da22dc79de1c9641fce2e6b565286aea1e094", "generation_seconds_batch": 25.024381004972383, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21183928847312927, "target_z": -0.2265625066723057, "ce": 6.229123115539551, "genuineness": 4.331617832183838, "identity": 0.623153567314148, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d6c955ef1500deb7533c7f9dc970fcb895a7ec5869241ce602e8cd62cdcfdc32.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "d6df58171f6cc5a43ae40ad2bb255471a24ba39c48b245baa8ddb2103cd93d0b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "73667dae3371f5fd62d3092365bbe88f5083155b29506b069edcc53c6e02013d", "generation_seconds_batch": 24.246200858033262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44765371084213257, "target_z": 0.11132813600930441, "ce": 5.879645347595215, "genuineness": 4.281409740447998, "identity": 0.4957507848739624, "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_Relief/d6df58171f6cc5a43ae40ad2bb255471a24ba39c48b245baa8ddb2103cd93d0b.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "d701717e7e610cc62534f9746fe4d0e6f470acd5e1f228315c67ef13727a216d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "9244436230dc56fc9ed309f9b9dc5141fd57e94285ed2306bccac2669a254143", "generation_seconds_batch": 17.364498949958943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4633292257785797, "target_z": 0.13378905999788535, "ce": 6.3641486167907715, "genuineness": 4.582659721374512, "identity": 0.5851970911026001, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d701717e7e610cc62534f9746fe4d0e6f470acd5e1f228315c67ef13727a216d.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "d8389f57fe1b33ef3a08ed75f217be025eec6f84b13354760396c47a58bfd4ff", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "5f7baa3544aa7b607ec13bce53aa7c71f0b1d6902c77b136ef7612b142482390", "generation_seconds_batch": 24.990833226009272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7979675531387329, "target_z": 0.613281189282018, "ce": 5.804190158843994, "genuineness": 4.406930446624756, "identity": 0.6508959531784058, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d8389f57fe1b33ef3a08ed75f217be025eec6f84b13354760396c47a58bfd4ff.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "d84ab2984c75eb79d99c62a6f68b1ef1d6716e24fec10aeb5ae87637b7779686", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "43df3807e66515a8b3943882257114669553e03038000971696f3e6efa98f0c7", "generation_seconds_batch": 21.988933731918223, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8197770118713379, "target_z": 0.6445312373226192, "ce": 6.23706579208374, "genuineness": 4.105680465698242, "identity": 0.3410860002040863, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d84ab2984c75eb79d99c62a6f68b1ef1d6716e24fec10aeb5ae87637b7779686.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "d9085208ccef112cae7e27a0ce02f7bcabbd947aac8abf0f506b724f8115c026", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e2b9fcefa779d1cd0ac0f9747742cea66ba55185fea478fd93c261945cf8fc02", "generation_seconds_batch": 22.335830855066888, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27590447664260864, "target_z": -0.1347656293369987, "ce": 6.173524379730225, "genuineness": 4.281409740447998, "identity": 0.5725224614143372, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d9085208ccef112cae7e27a0ce02f7bcabbd947aac8abf0f506b724f8115c026.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "d91d4b45d03b1807d9cb7525f7739f7cfb0d1cf5ab9953905a682afb2e010897", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "05f569206ff7e4df3f59650684e9a97e2b4d559aefb5e5728426ec483461cee8", "generation_seconds_batch": 18.501691431971267, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2513688802719116, "target_z": -0.16992186932854014, "ce": 6.2767791748046875, "genuineness": 4.444586753845215, "identity": 0.5437083840370178, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d91d4b45d03b1807d9cb7525f7739f7cfb0d1cf5ab9953905a682afb2e010897.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "d94a4d07c89c2a389e37002fa50d8dbe8f5358081ad0d433cdbdc84b0f4df284", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 2.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "248e53ccaa0584fa008c54ff47a725b73c0495886981a2ab48c355af53410b7a", "generation_seconds_batch": 16.304784015985206, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5253497958183289, "target_z": 0.22265627201860883, "ce": 6.09409761428833, "genuineness": 4.319066047668457, "identity": 0.6405235528945923, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/d94a4d07c89c2a389e37002fa50d8dbe8f5358081ad0d433cdbdc84b0f4df284.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": "d97bccce179258d24d28afbf74b907f19cf8306f8daf7702c1db02a16e715382", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "963e884f7039ab6c96a85b615aaea8dcdc514db1a31da935b07128ce394e70ef", "generation_seconds_batch": 25.353885357966647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44594985246658325, "target_z": 0.1088867340128993, "ce": 6.403861999511719, "genuineness": 4.017816066741943, "identity": 0.21050558984279633, "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_Relief/d97bccce179258d24d28afbf74b907f19cf8306f8daf7702c1db02a16e715382.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": "d9bec0f126b960ecf6b3561713c1e67119c09dfb955b21b8a26c8d40fdb518ab", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La route tourne à gauche après le pont.\n(Natural clear speech.) [3.8 seconds duration] Continue... jusqu’à la petite barrière en bois.\n(Natural clear speech.) [3.2 seconds duration] Je t’attendrai de l’autre côté.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "cbf6e01945591a8bbf980213144c9031fd03e5a5ff348137c355f7a450689b7e", "generation_seconds_batch": 17.190826967009343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5798733234405518, "target_z": 0.30078122130908547, "ce": 6.133810997009277, "genuineness": 4.68307638168335, "identity": 0.8517425060272217, "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_Relief/d9bec0f126b960ecf6b3561713c1e67119c09dfb955b21b8a26c8d40fdb518ab.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "dafb7e8723fbbfc093e2a2f8e3cca47963ff66de7f8ef7a53973ff888f1d0efc", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c696a9b6ed637be7408fd05e68b6b2e901169c50d48e85026eb561e1af55a994", "generation_seconds_batch": 22.545159319997765, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4549765586853027, "target_z": 1.5546875413682955, "ce": 6.062326908111572, "genuineness": 4.005263805389404, "identity": 0.5516499280929565, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/dafb7e8723fbbfc093e2a2f8e3cca47963ff66de7f8ef7a53973ff888f1d0efc.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "50e48c0fcc926f4846fd3898937760e83e4367e9ab0be8a0b484a09be224ad5e", "generation_seconds_batch": 18.659329934045672, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.358371376991272, "target_z": -0.016601550656657367, "ce": 6.356205940246582, "genuineness": 4.243753433227539, "identity": 0.37003621459007263, "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_Relief/db192910e9ae67de251fb2a990940eab881f66f627c78b50b638ce61f5a63679.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "db6bb64dff341a6f39225d77f6b2c367bd84b1cafca361ef8fb83c2f509559a2", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 2.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9a6a36a349a74c6b5bebc12fae8bc3dd02ee030eb2429f72f29de6568b08aec4", "generation_seconds_batch": 20.429997662082314, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8361340761184692, "target_z": 0.6679687306503135, "ce": 6.229123115539551, "genuineness": 3.8169827461242676, "identity": 0.37306874990463257, "hypothesis": "The 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_Relief/db6bb64dff341a6f39225d77f6b2c367bd84b1cafca361ef8fb83c2f509559a2.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": "dc109e71e7b02ba44efcb33f44135214a91512d3dcc68066ad100099798eb6b8", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e5c7d09dd75cfb7426080cd8406d598fe5e33f0cedffb0c214d47c390bdb5858", "generation_seconds_batch": 19.680780119961128, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22819636762142181, "target_z": -0.20312499199323314, "ce": 6.221180438995361, "genuineness": 4.432034492492676, "identity": 0.6560056209564209, "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_Relief/dc109e71e7b02ba44efcb33f44135214a91512d3dcc68066ad100099798eb6b8.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "dc27d7bf90980f0837876191059532016547325f9866e0d4ac1ce9cb2a26c8e1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "1cdf97d154e9ac43b5111915eb4e010b1bd4f42191e9c93becd8ae5c9a16e5b8", "generation_seconds_batch": 18.742833688040264, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9315503239631653, "target_z": 0.8046874986655389, "ce": 6.181467056274414, "genuineness": 4.369274139404297, "identity": 0.418900728225708, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/dc27d7bf90980f0837876191059532016547325f9866e0d4ac1ce9cb2a26c8e1.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "dc890f8d5dd4bad15016bf69b25d46f53784069f1ddf2da14144dd1ab27ebd2f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "864b675aa77e4ed1247c59c42a245c535b5bc3677fdf35d6e523a24336b69fde", "generation_seconds_batch": 24.990833226009272, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.988800048828125, "target_z": 0.8867187253124689, "ce": 5.927301406860352, "genuineness": 4.507347106933594, "identity": 0.7111771106719971, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/dc890f8d5dd4bad15016bf69b25d46f53784069f1ddf2da14144dd1ab27ebd2f.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "dc9637f6501c840ec5110446265942171cdff04b881bad0ad75586dbd1d3b0e4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "8050c5e5842353d852f8a540a8268ec9b4d426001fd14aa48783cdf1b886ca88", "generation_seconds_batch": 22.309621657943353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2609105110168457, "target_z": -0.1562499839864663, "ce": 6.125868320465088, "genuineness": 4.20609712600708, "identity": 0.7369582653045654, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/dc9637f6501c840ec5110446265942171cdff04b881bad0ad75586dbd1d3b0e4.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": "dd359741d3a8f3039f27ce641f47c5b57b759c167fb46a5f99a8e1530cfb6777", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Quelqu’un a déplacé la petite chaise bleue.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était ici... près de la grande bibliothèque.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "84d88352ed9d7a619f3f2ed6a48bc44848bb6f940434266fff35fb8348acd1fb", "generation_seconds_batch": 23.105727571062744, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3866554796695709, "target_z": 0.023925799348629234, "ce": 6.2767791748046875, "genuineness": 4.444586753845215, "identity": 0.7225157022476196, "hypothesis": "Quelqu'un a déplacé la petite chaise bleue. Elle était ici, près de la grand bibliothèque. Nous la remetrons après le déjeuner.", "wer": 0.09523809523809523, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/dd359741d3a8f3039f27ce641f47c5b57b759c167fb46a5f99a8e1530cfb6777.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "dd8f23716a06a518fe1bf09c5433a55aed3865554ca397ef00a972c003616027", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "abfa1482766a62cd59b09cf0ddfa646deb3ecdbbfc43445eb80f86cd87b4dfd6", "generation_seconds_batch": 25.018009713036008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.15731573104858398, "target_z": -0.30468749866553885, "ce": 6.173524379730225, "genuineness": 4.532451152801514, "identity": 0.5159991979598999, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/dd8f23716a06a518fe1bf09c5433a55aed3865554ca397ef00a972c003616027.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": "dda142665f1ed3892bf8f5ad41c671f044c6d37cfeb59bc000ff1044c382d141", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e62f1679ca706860eb909e84ced4bf80c3e59d09d13ab64009632cdff4ffe6de", "generation_seconds_batch": 19.07860932603944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4176657497882843, "target_z": 0.06835938400761271, "ce": 6.062326908111572, "genuineness": 4.68307638168335, "identity": 0.8548885583877563, "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_Relief/dda142665f1ed3892bf8f5ad41c671f044c6d37cfeb59bc000ff1044c382d141.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "ddf3afb6a50892f55426b2904bcf509c50e78f77ee417eca3e014484d120bea1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "47cb5bf44971bdc4c28aba92ef5d8f9c9bdc3a4758148b114957755f133c944f", "generation_seconds_batch": 22.226476851967163, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.20194935798645, "target_z": 2.6250000213513784, "ce": 6.09409761428833, "genuineness": 4.293961524963379, "identity": 0.6623715162277222, "hypothesis": "I've trouved the petite boîte. Elle était près de la vieille fenêtre. We've regarded.", "wer": 0.5263157894736842, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ddf3afb6a50892f55426b2904bcf509c50e78f77ee417eca3e014484d120bea1.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "de32f6a4e1cdc2afe98da9afc4060c0a30f8968d11294468a88637fa01f27df7", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e55b0e5af5df5674febbb9c07d0bf8dadfad6c292991248dbc97420a234efb0f", "generation_seconds_batch": 23.614297808962874, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5716947913169861, "target_z": 0.2890624746452383, "ce": 6.284721851348877, "genuineness": 4.15588903427124, "identity": 0.3978908956050873, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/de32f6a4e1cdc2afe98da9afc4060c0a30f8968d11294468a88637fa01f27df7.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "de8ff8fe88d0b0084414ebdf8a3625b292fcec2a446dd5dfb85ab0c06cfc6bbe", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e18a78279432b6c6da70459e34ba350dbc3e7ca392511b21cd7c9750eef7bc9b", "generation_seconds_batch": 26.02227647602558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.32327181100845337, "target_z": -0.06689455135032095, "ce": 5.919358730316162, "genuineness": 3.722842216491699, "identity": 0.32576656341552734, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/de8ff8fe88d0b0084414ebdf8a3625b292fcec2a446dd5dfb85ab0c06cfc6bbe.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "ded1dc7f0c9225a8dd719de877bc1a8e1bc0efaf2860777971ff4134dfad6a10", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "1dca0ac0ebfde1b66d00d860f6b62192c1115ad1abe0790a8550cd40a93ebd3a", "generation_seconds_batch": 18.484454660094343, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0733115673065186, "target_z": 1.0078124693073938, "ce": 6.022613525390625, "genuineness": 3.9425034523010254, "identity": 0.4340701699256897, "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_Relief/ded1dc7f0c9225a8dd719de877bc1a8e1bc0efaf2860777971ff4134dfad6a10.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "dff84c84432d9167aba476ba5ff34bd34d6fee155ef0c51df7faac11eb0fe898", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "fa7466581ccfd2f1360266d73485a0e325b2fbbf9a9d9039f34f4bb6514a1b7f", "generation_seconds_batch": 15.914702903013676, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9615382552146912, "target_z": 0.847656207964474, "ce": 6.046441555023193, "genuineness": 4.507347106933594, "identity": 0.7159942984580994, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/dff84c84432d9167aba476ba5ff34bd34d6fee155ef0c51df7faac11eb0fe898.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "e0bb0cb8aef3a1ba61b5b2ad38dae43fc15a630f55d593d8ab842850e90afebf", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c09916acfe0edd5d32247cf9da7824ecb24729366b0be961f1fc6717d637247f", "generation_seconds_batch": 18.385925302980468, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.40659064054489136, "target_z": 0.05249022832822295, "ce": 6.221180438995361, "genuineness": 4.65797233581543, "identity": 0.6657896041870117, "hypothesis": "La porte est encore ouverte. J'ai poussé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e0bb0cb8aef3a1ba61b5b2ad38dae43fc15a630f55d593d8ab842850e90afebf.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": "e0d85d1df7e7ebd62438d4976e5f6aed8b3d4fe03a7fefe5ba74d86179f0ef47", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "c5609ae96e371ac6b9bf10bea0749ff83d1d33b0ac82192d5b6ac0b19a403079", "generation_seconds_batch": 18.683470105053857, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2806752920150757, "target_z": -0.12792968666596177, "ce": 6.133810997009277, "genuineness": 4.519899368286133, "identity": 0.6022419929504395, "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_Relief/e0d85d1df7e7ebd62438d4976e5f6aed8b3d4fe03a7fefe5ba74d86179f0ef47.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "e10b0ce3251002075ad2758dbfb6bb804392fcfb0939aacb0063778255322255", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear speech.) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Natural clear speech.) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "seed": 1702, "scale": 0.75, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fa7297c78a0ba3f191b5890f5febed9f71b4086eb255848d51cfcfe4c2fd030f", "generation_seconds_batch": 27.348741577006876, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9233717918395996, "target_z": 0.7929687520016917, "ce": 6.268836498260498, "genuineness": 4.306513786315918, "identity": 0.5040006637573242, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinfliegen.", "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_Relief/e10b0ce3251002075ad2758dbfb6bb804392fcfb0939aacb0063778255322255.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "e1590292a710e1daed5f742aed9d4179d8dfb7e0456d47f185f9f86033ad927e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "81cc4a2dd2a0550fd079098150f21d423504b7cd1419b18b69ce6bb14000836f", "generation_seconds_batch": 32.19138946698513, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24182724952697754, "target_z": -0.183593754670614, "ce": 6.300607204437256, "genuineness": 4.582659721374512, "identity": 0.526544988155365, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e1590292a710e1daed5f742aed9d4179d8dfb7e0456d47f185f9f86033ad927e.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "e1eaad11d8a3a3512f904732268add43354d56f7f7790fe9b8c80b67ef1cdc96", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "45601591340e7a0ea5bca5996601e038fbacb603394037b63e9baa4736f1004e", "generation_seconds_batch": 22.998699732939713, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1550970077514648, "target_z": 1.1250001067568913, "ce": 6.173524379730225, "genuineness": 4.15588903427124, "identity": 0.5231941342353821, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e1eaad11d8a3a3512f904732268add43354d56f7f7790fe9b8c80b67ef1cdc96.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "e1fd48ed21cb6d754a294f32a090f5c80d325f1e95ad1df20104ae1853d8e6da", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5f8bef0f9e0a14de6cb145162a893771cf70b69ed468ba9e014757e490f5fa2e", "generation_seconds_batch": 21.56574918399565, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3508743643760681, "target_z": -0.027343770684147693, "ce": 6.308549880981445, "genuineness": 4.507347106933594, "identity": 0.6917104721069336, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e1fd48ed21cb6d754a294f32a090f5c80d325f1e95ad1df20104ae1853d8e6da.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "e200c4387b6f5b855e752c7631ebe007e7317fbe81d078b7ed9465238bea81e1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "44c12df4f84b89d440b13d53c76e22ddad539ca606285f5818d47bfba89197ec", "generation_seconds_batch": 24.85053160006646, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44697216153144836, "target_z": 0.11035156667019107, "ce": 6.3641486167907715, "genuineness": 4.20609712600708, "identity": 0.595532238483429, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e200c4387b6f5b855e752c7631ebe007e7317fbe81d078b7ed9465238bea81e1.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "e206754556871079e96eea00a45ed3daf57177e038c8b65fe7f73d4bfa627a61", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Natural clear speech.) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "seed": 1702, "scale": 0.0, "cfg": 2.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "c2c600e4bb91c4c1f7d5ed2d3bc622e40ae90f8fb820fa58cd341586c15f16b5", "generation_seconds_batch": 18.674831525073387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0651330947875977, "target_z": 0.9960938080490597, "ce": 6.268836498260498, "genuineness": 4.570107460021973, "identity": 0.62791907787323, "hypothesis": "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_Relief/e206754556871079e96eea00a45ed3daf57177e038c8b65fe7f73d4bfa627a61.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "e2593ca09f16e122020ffc93f567164bd84eb028b27e377a7e4d8830b3ccd04e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "16cd42cabea4bc08ed6b018ddde96831cbc1b517f65291e8697f455e2f23c270", "generation_seconds_batch": 26.4223464820534, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8093795776367188, "target_z": 2.062499839864663, "ce": 6.141753673553467, "genuineness": 4.444586753845215, "identity": 0.6882514953613281, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e2593ca09f16e122020ffc93f567164bd84eb028b27e377a7e4d8830b3ccd04e.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": "e2721965209296b864bbc0491c3f395b7887ebea853f69bf29de51431220b91b", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai écrit le numéro sur l’enveloppe.\n(Natural clear speech.) [3.8 seconds duration] Lis-le bien... et vérifie les deux derniers chiffres.\n(Natural clear speech.) [3.2 seconds duration] Appelle-moi quand tu auras un moment.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3c2a4869aa66ddd48fa6b0c77afc144780ab98455365524d5ad902a7070bd3e2", "generation_seconds_batch": 19.564371157088317, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7625272870063782, "target_z": 0.5625000106756891, "ce": 5.911416053771973, "genuineness": 4.425758361816406, "identity": 0.5564446449279785, "hypothesis": "J'écris le numero sur l'enveloppe. Lille and verify les two derniers chiffres. Appelle moi quand you're a moment.", "wer": 0.5454545454545454, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e2721965209296b864bbc0491c3f395b7887ebea853f69bf29de51431220b91b.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": "e39a1f2a92f57f8b8800f4543b9fce108521509419d54cde55840cef6e0fb930", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Schlüssel liegen auf dem Küchentisch.\n(Natural clear speech.) [3.8 seconds duration] Ich suchte in der Schublade... dann neben dem Fenster.\n(Natural clear speech.) [3.2 seconds duration] Nimm sie mit, wenn du gehst.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "d673b539e263ffc9bbbe9c68a9eefa364f8b471a192bfceb6bbcc81dd3f6562f", "generation_seconds_batch": 17.74637057702057, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.47696012258529663, "target_z": 0.15332031867188278, "ce": 6.260893821716309, "genuineness": 4.381826400756836, "identity": 0.5252248048782349, "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_Relief/e39a1f2a92f57f8b8800f4543b9fce108521509419d54cde55840cef6e0fb930.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": "e3b01f6800b0cef7c278f2607f16d6ff1f2506cbd63ba809d4bf46dce6ec0202", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Ik wacht aan de andere kant.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De weg gaat linksaf na de brug.\n(Natural clear speech.) [3.8 seconds duration] Loop verder... tot aan het kleine houten hek.\n(Natural clear speech.) [3.2 seconds duration] Ik wacht aan de andere kant.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1774573e9e61d13401563a4ba6956ba45b9a1fb9c3c12fe265a22ea9458db804", "generation_seconds_batch": 19.85053206095472, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.31032246351242065, "target_z": -0.08544924068520501, "ce": 6.181467056274414, "genuineness": 4.482243061065674, "identity": 0.6842674612998962, "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_Relief/e3b01f6800b0cef7c278f2607f16d6ff1f2506cbd63ba809d4bf46dce6ec0202.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": "e3c80b9d80461043bf40119bd63c48339cf7be9f353a3f1ef45f3d98f50891f0", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6fbe7cabe5c3e8a3b078643045b152b1b0f37ef982681ece1878cad7cfcf35b1", "generation_seconds_batch": 25.247655697050504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3931301534175873, "target_z": 0.033203144016071266, "ce": 5.903473377227783, "genuineness": 4.400654315948486, "identity": 0.6324082612991333, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends les quand tu partiras?", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e3c80b9d80461043bf40119bd63c48339cf7be9f353a3f1ef45f3d98f50891f0.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "e422b39d94ce475f7b590fd1a7300397cbc07a45b8fb416ed5bfcebeb6dcd597", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "f105cefcc244bff72865d0ecdfc5ce1f153746d6eb57f46f902c0034b27f9e22", "generation_seconds_batch": 24.314618165954016, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4059052467346191, "target_z": 1.4843748905741865, "ce": 6.324435234069824, "genuineness": 4.582659721374512, "identity": 0.6011955738067627, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e422b39d94ce475f7b590fd1a7300397cbc07a45b8fb416ed5bfcebeb6dcd597.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "e423d0f3859104cf31ee40ab03752aa833223a00c6669f1208b327af8b2ba0d6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "48a2572bd611f9284b700a311bf3205fed63c0ef77373459c04cf74f03ed0acc", "generation_seconds_batch": 26.54470519197639, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20638693869113922, "target_z": -0.23437499733107772, "ce": 6.2767791748046875, "genuineness": 4.337893962860107, "identity": 0.5169498920440674, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e423d0f3859104cf31ee40ab03752aa833223a00c6669f1208b327af8b2ba0d6.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "e431af2d47023177f4d2134a10f05406b8a11f26fef161ff0db80e8a86399b9d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "456ac69952d7124df426192216568e86ef54fdf8b191696ffe7257878b81d113", "generation_seconds_batch": 25.246419003000483, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14504793286323547, "target_z": -0.3222656186613096, "ce": 5.998785495758057, "genuineness": 4.017816066741943, "identity": 0.41962912678718567, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e431af2d47023177f4d2134a10f05406b8a11f26fef161ff0db80e8a86399b9d.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "e43c2f4079a7c8a00bb3758dd9857ff37dadca47c41210402b35f7f7593415f2", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds 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": "417198781bd45f80c02710a0b80c9304f5e17a01ff49406d34c8076cf298dd2a", "generation_seconds_batch": 25.14602584205568, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.694372832775116, "target_z": 0.46484376000845856, "ce": 6.149696350097656, "genuineness": 4.607763767242432, "identity": 0.7416833639144897, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e43c2f4079a7c8a00bb3758dd9857ff37dadca47c41210402b35f7f7593415f2.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "e48c24f124c9b62a6cac2c874484fbecacdd17a1a48892f8cb46af673e3c397b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "9ba3c5f135db0cd56a0f254de9b2b575fddb8f4087c8e3aca2fbafeecfa40294", "generation_seconds_batch": 24.76645421795547, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.22819636762142181, "target_z": -0.20312499199323314, "ce": 5.990842819213867, "genuineness": 4.049196243286133, "identity": 0.5442390441894531, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e48c24f124c9b62a6cac2c874484fbecacdd17a1a48892f8cb46af673e3c397b.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "e4ab01e6c10cc3839724214bbd18a38dac495858aa5947f1ae8ff085f21a2fea", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "268b8f5ae852709dab671a96669212b695b4bf74c21829860327426b7986f347", "generation_seconds_batch": 23.341405760962516, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6493908762931824, "target_z": 0.40039061065454273, "ce": 6.4515180587768555, "genuineness": 4.369274139404297, "identity": 0.6046164035797119, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e4ab01e6c10cc3839724214bbd18a38dac495858aa5947f1ae8ff085f21a2fea.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": "e4e91b14780f89275494b514a6450de0641c156a282e83a115508d695458fc3c", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik schreef het nummer op de envelop.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lees het goed... en controleer de laatste twee cijfers.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "0baf5f3b57204aa08aaba0b06cfe04a8aeddcadfe8eae16660a4e4eaa68283aa", "generation_seconds_batch": 21.91696039296221, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.19548222422599792, "target_z": -0.25, "ce": 6.316492557525635, "genuineness": 4.507347106933594, "identity": 0.7853947877883911, "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_Relief/e4e91b14780f89275494b514a6450de0641c156a282e83a115508d695458fc3c.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "e59b851ee6f501ab31ecdd6644d027497465a7eb51690d57169934f90988c5c1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "e2040b7c83de6d85ff3d7673fddd7022a69bc086960201a87e3d4bb10625ea5a", "generation_seconds_batch": 24.91507266892586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5219420790672302, "target_z": 0.2177734680257986, "ce": 6.268836498260498, "genuineness": 4.055472373962402, "identity": 0.23676282167434692, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e59b851ee6f501ab31ecdd6644d027497465a7eb51690d57169934f90988c5c1.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "e67f2101f95cc41003d51cfea2a7d4dd9d4f6d7a74758c3191c8a14657bee964", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "da8d40c5ccf4f1757389f5938d7943ae55a6305bc0c2ca4b6786a428b2944b2d", "generation_seconds_batch": 23.60475362103898, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.568968653678894, "target_z": 0.285156282694298, "ce": 6.197352409362793, "genuineness": 4.482243061065674, "identity": 0.6920180320739746, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e67f2101f95cc41003d51cfea2a7d4dd9d4f6d7a74758c3191c8a14657bee964.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "bdf9f0b24ced71ad77839f76f3e811b7dcfa5a23e6f58ded43f92f920c602b01", "generation_seconds_batch": 16.897238890989684, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21047620475292206, "target_z": -0.22851562399915415, "ce": 6.308549880981445, "genuineness": 4.168440818786621, "identity": 0.36423447728157043, "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_Relief/e6f1e80cc6606ef00fdc322d5829b94fd65ad80a74ab015f88321e5dc194804c.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "e7786c07511b05e1284752a1d9a4b81e3b04508edbff20ded811f08a1254b773", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "ee648843f0aee0d41e105d1100fa0188336e19d9d318b0aa7d27e56ea50a54c7", "generation_seconds_batch": 22.187126793083735, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5539746284484863, "target_z": 0.2636718426393173, "ce": 6.149696350097656, "genuineness": 4.545003414154053, "identity": 0.6222383975982666, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e7786c07511b05e1284752a1d9a4b81e3b04508edbff20ded811f08a1254b773.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "e7fddc24b6114f2eee1dda3f0e0fa912892c27ee5446f5bea42693d51bd74846", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5380902d7b9e43fae50faf669e4354a8dd3cc5cd03c45b21a4a8c27654d6e2ad", "generation_seconds_batch": 21.07569629396312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6125874519348145, "target_z": 0.34765620796447405, "ce": 6.213237762451172, "genuineness": 4.469690799713135, "identity": 0.672099232673645, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e7fddc24b6114f2eee1dda3f0e0fa912892c27ee5446f5bea42693d51bd74846.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": "e8083c1433a5b1f075c039880c7f7ff2dab34fa07d2e8ad8126b2faee478b926", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I wrote the number on the envelope.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Read it carefully... and check the last two digits.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2e9e8e139245942289e2e3272c23202f705111e4edcb53cab1e12a18545b7fdc", "generation_seconds_batch": 25.522787277936004, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.694372832775116, "target_z": 0.46484376000845856, "ce": 6.427689552307129, "genuineness": 4.162164688110352, "identity": 0.32036733627319336, "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_Relief/e8083c1433a5b1f075c039880c7f7ff2dab34fa07d2e8ad8126b2faee478b926.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "e8994f82c992ec5ab9ee0d1771b61c64204f5e2a85563adbb21c2a663f4a697e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "e4cff3bea00cbf5001f47b5439fc0eae544125b1e6f0d2831ab98aa442f097a0", "generation_seconds_batch": 19.16009701602161, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.6239995956420898, "target_z": 1.796875029358145, "ce": 6.157639026641846, "genuineness": 4.375550270080566, "identity": 0.439480721950531, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e8994f82c992ec5ab9ee0d1771b61c64204f5e2a85563adbb21c2a663f4a697e.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "e8a0ad9e53ff7779ac8b98c3b34d3345ccf582e544159029c36680058ca007de", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "dcc5818476603d04fb0fce077ac5ece3e7e3e91a5ba642f23962dd9397de46a2", "generation_seconds_batch": 25.94559709506575, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2586917877197266, "target_z": 1.273437621435964, "ce": 6.1894097328186035, "genuineness": 4.293961524963379, "identity": 0.7120746970176697, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what continues.", "wer": 0.3157894736842105, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e8a0ad9e53ff7779ac8b98c3b34d3345ccf582e544159029c36680058ca007de.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "e8b475b2936f6d9442aa9eeaba2b8eaccfd7f00973c2b9bfdfa855bb9f669c1e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "cb623c839a6ecdd68051e84b54f1ed3e75325cc14abbfa46e34132bfd5da364f", "generation_seconds_batch": 24.321183460997418, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4168100357055664, "target_z": 1.5, "ce": 6.268836498260498, "genuineness": 4.369274139404297, "identity": 0.7273200154304504, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble what 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_Relief/e8b475b2936f6d9442aa9eeaba2b8eaccfd7f00973c2b9bfdfa855bb9f669c1e.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "e9040ec361f9ff11ad63d14b65ce22f04dcc684c84ff8fa77ea344553cc14f01", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "44ea5b96a8fcb30476931098cb20139c236f118b277a83ae9b1782ca29e8a9f0", "generation_seconds_batch": 23.781606448930688, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.09597671031951904, "target_z": -0.39257814134714897, "ce": 6.022613525390625, "genuineness": 4.218649387359619, "identity": 0.5411680936813354, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e9040ec361f9ff11ad63d14b65ce22f04dcc684c84ff8fa77ea344553cc14f01.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "e959737e231ca7e08bbaf9a43699866e4bc846d203e121fb75af5f1379c0808b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "bcd50ae4d53c42764da2586c4619b4fb74c6e151f1e1391f89aecff2d75323e2", "generation_seconds_batch": 21.509229005896486, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.21320238709449768, "target_z": -0.22460936799407902, "ce": 6.2767791748046875, "genuineness": 4.507347106933594, "identity": 0.7731082439422607, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd, zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e959737e231ca7e08bbaf9a43699866e4bc846d203e121fb75af5f1379c0808b.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": "e9d092c4e0d65b4390be06c8cb351d6e3521694e966e0d6adbaf99a7b06cc614", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "29d8f6b156ce64f67ca53d1ac90996356fd53bcedb1777f2550594adb3f9673b", "generation_seconds_batch": 17.923446572036482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8988361954689026, "target_z": 0.7578125120101503, "ce": 6.300607204437256, "genuineness": 4.570107460021973, "identity": 0.6299940347671509, "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_Relief/e9d092c4e0d65b4390be06c8cb351d6e3521694e966e0d6adbaf99a7b06cc614.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "e5f2fa7da5a89648e30f1b5497ab8a0d4406132896da9af51f8d88bfc2e6dce5", "generation_seconds_batch": 16.89595431298949, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20775002241134644, "target_z": -0.23242188000422928, "ce": 6.4912309646606445, "genuineness": 4.632867813110352, "identity": 0.656121015548706, "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_Relief/e9d266c3907611a53d0c5f7688a7e231bba29ead6f87b8ae8d29cb37ab2fae41.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "e9e2dd642bfa81cee39d1d9a7d564bb5762d0e86473386bef3696d324827daea", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "329ca390d94a97c556a4df341ace5d3c2fd959f4d8d1804805df5e129e1954a5", "generation_seconds_batch": 19.119071808992885, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.5204048156738281, "target_z": 1.6484375146790726, "ce": 6.268836498260498, "genuineness": 4.406930446624756, "identity": 0.5537606477737427, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e9e2dd642bfa81cee39d1d9a7d564bb5762d0e86473386bef3696d324827daea.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "e9efe23095d73f2fdb0ba333f83452837f1ce88143dc706e903bcf31e2e4449f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "c4d1a55080711810996a7b7ef28f65425a337805ffa3b5298112702343c86b0b", "generation_seconds_batch": 18.674831525073387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45719534158706665, "target_z": 0.12500002135137828, "ce": 6.109982967376709, "genuineness": 4.570107460021973, "identity": 0.747114896774292, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/e9efe23095d73f2fdb0ba333f83452837f1ce88143dc706e903bcf31e2e4449f.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "ea77dcbe7bc003f329776dee4f1c29897578093af0b1ebd966b7d930459c8b7a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "2bb82753a1a3ecff25d06df9650b3118eeffa6ac02dfc9e7f9428b58624d2c44", "generation_seconds_batch": 22.337986020022072, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8579435348510742, "target_z": 0.6992187786909145, "ce": 5.808161735534668, "genuineness": 3.8671910762786865, "identity": 0.30206024646759033, "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_Relief/ea77dcbe7bc003f329776dee4f1c29897578093af0b1ebd966b7d930459c8b7a.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "eac5ea0f1f77c93608bf78194d72e6a9376ea4e7fbdc48b971caa805a9ae7a07", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 0.0, "cfg": 1.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "dcc55f6cdb2af584f66b896ea1ea369591ee0959548606b9a40af0b2a22aec3c", "generation_seconds_batch": 20.177506292006, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.14095866680145264, "target_z": -0.32812499199323314, "ce": 6.109982967376709, "genuineness": 4.2249250411987305, "identity": 0.6596732139587402, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/eac5ea0f1f77c93608bf78194d72e6a9376ea4e7fbdc48b971caa805a9ae7a07.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "eb37303a38d03e385c780307157c000210f6e12b8b7eb6236117f447fb8b4402", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "160a7297ff31915635814965fcdc6c65e81fdfc86fe9d5662088f7740254be46", "generation_seconds_batch": 23.202106893993914, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.1259646862745285, "target_z": -0.349609367994079, "ce": 6.1020402908325195, "genuineness": 4.256305694580078, "identity": 0.5289366245269775, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/eb37303a38d03e385c780307157c000210f6e12b8b7eb6236117f447fb8b4402.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "eb82413557c9e95da5d545247b1d8778fac158991de32eec1694239bfb67d6b9", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "ea76f42eed29df61b4d0eeae26763b9c927068631fba520dca2718674715ceea", "generation_seconds_batch": 21.477924001053907, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38699623942375183, "target_z": 0.024414062666807644, "ce": 6.1020402908325195, "genuineness": 3.9676074981689453, "identity": 0.32833853363990784, "hypothesis": "The 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_Relief/eb82413557c9e95da5d545247b1d8778fac158991de32eec1694239bfb67d6b9.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "e1ab2bca9c950dbafe14a077b09291dcd94fb0ae004c793ab8bff6b6be2c848a", "generation_seconds_batch": 18.5264182779938, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.11914923787117004, "target_z": -0.3593749973310777, "ce": 6.149696350097656, "genuineness": 4.268857479095459, "identity": 0.820242166519165, "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_Relief/ebe89981a89e9506d02bacdfa583f9bfe1f04faa699193749ab6419de85c588f.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "ec520d250e17e836b8d877f4149951f4e9ff904932defddc5c91bdac17c1290b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "seed": 1702, "scale": 1.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "fc7140141c43f0d88762f77a1ebb17ec9240f2c255c1dd733c3106dc3b828bd5", "generation_seconds_batch": 24.01444022997748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.191044569015503, "target_z": 2.6093749119255647, "ce": 5.9431867599487305, "genuineness": 4.532451152801514, "identity": 0.5475030541419983, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble.", "wer": 0.15789473684210525, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ec520d250e17e836b8d877f4149951f4e9ff904932defddc5c91bdac17c1290b.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "ec74ed6f792cdb9812e9e7396f3b1e9825faba29bb019ea3c26d80cde8a76cf0", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "75387d5ef73e77ca369ac4d29537537cb56a5874e33cbf44616da746b14c868f", "generation_seconds_batch": 22.309621657943353, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.42107346653938293, "target_z": 0.07324218800042293, "ce": 6.086154937744141, "genuineness": 4.369274139404297, "identity": 0.6942535638809204, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ec74ed6f792cdb9812e9e7396f3b1e9825faba29bb019ea3c26d80cde8a76cf0.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "ec8bb1f49d6974ba65fe1d6cb84194822acac4eec373c26f2c0c161faa6a42ba", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "55816bea80e18b5f6343532ecd70a08c9b68b90c41fc9a13f968ee13a6aedf44", "generation_seconds_batch": 20.886213725083508, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.8311891555786133, "target_z": 2.09375005871629, "ce": 6.324435234069824, "genuineness": 4.369274139404297, "identity": 0.37893402576446533, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ec8bb1f49d6974ba65fe1d6cb84194822acac4eec373c26f2c0c161faa6a42ba.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "ed2add4cfba54222a312bb3ef45200f52a33f85ab01b647bf2e428543dbec981", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "470845d22aa7497c2c531b4a713849de6b30b87fe033b62ba0f8718ca6272943", "generation_seconds_batch": 23.15395933703985, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5989565849304199, "target_z": 0.32812499199323314, "ce": 6.23706579208374, "genuineness": 4.137060642242432, "identity": 0.5719509124755859, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ed2add4cfba54222a312bb3ef45200f52a33f85ab01b647bf2e428543dbec981.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "ed904e39618294c918bd43b6368e6f4eccaa9032bb1e41f9c2977b748e9a5517", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "b1d79919f324baeb827bdc01a2edaa28c455f806b41da91a51d852bea6a8a4c3", "generation_seconds_batch": 23.585255458019674, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6071351170539856, "target_z": 0.3398437386570803, "ce": 6.205295085906982, "genuineness": 4.413206577301025, "identity": 0.5489362478256226, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ed904e39618294c918bd43b6368e6f4eccaa9032bb1e41f9c2977b748e9a5517.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "edaecf07cf11cec3b41fb664ed35282870707f9b4b2a13511fdb7b541ad55a31", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "d39a991976ead7d2fc532be7baa3b8bd6831204281161105f6ff7b9e4d48040c", "generation_seconds_batch": 24.246200858033262, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.4168100357055664, "target_z": 1.5, "ce": 5.895530700683594, "genuineness": 4.168440818786621, "identity": 0.4878796339035034, "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_Relief/edaecf07cf11cec3b41fb664ed35282870707f9b4b2a13511fdb7b541ad55a31.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "ee6a10534c15be927612ce2342fa73973f77cc1646e85841fb8c129b807ff7bb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "d66538bbec949515490cc2b437072ef55fa04616b544f79c1b2b8a03769ea946", "generation_seconds_batch": 15.923540688934736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4398159384727478, "target_z": 0.10009765266363568, "ce": 6.427689552307129, "genuineness": 4.250029563903809, "identity": 0.5186874270439148, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ee6a10534c15be927612ce2342fa73973f77cc1646e85841fb8c129b807ff7bb.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "ee722d2615c1701c751a1674cb5e8f6eab2943831a38d7e1f63611e80979c93d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "53a24c91583304cb001d3869dd227c6f6814899d3495aafd3d4e141d529c7ed3", "generation_seconds_batch": 23.383719385019504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.34576278924942017, "target_z": -0.03466797667336303, "ce": 6.062326908111572, "genuineness": 3.9048471450805664, "identity": 0.4851548969745636, "hypothesis": "The 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_Relief/ee722d2615c1701c751a1674cb5e8f6eab2943831a38d7e1f63611e80979c93d.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "eebdda89c876ffe6e2dde2b17aecf472e00649669cb9a0e00ee71d254374c181", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "a3f0077423ce6350f9914e046b355f3d8387b1dd3bce2aa2a32e28d42bb9f074", "generation_seconds_batch": 25.018009713036008, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23501180112361908, "target_z": -0.1933593840076127, "ce": 6.078212261199951, "genuineness": 4.369274139404297, "identity": 0.5241096019744873, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/eebdda89c876ffe6e2dde2b17aecf472e00649669cb9a0e00ee71d254374c181.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": "eed1ea2799bee37f4be30e37a99339706e54e3a3afd706621feda3841b1cb24d", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "f9f8bcb362f802a672bb4fa6b6fe2e7e7acc9e54c0fdd76d6e309103dd86e444", "generation_seconds_batch": 23.96158161899075, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.33605077862739563, "target_z": -0.04858399367452608, "ce": 6.316492557525635, "genuineness": 4.174716949462891, "identity": 0.5149189233779907, "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_Relief/eed1ea2799bee37f4be30e37a99339706e54e3a3afd706621feda3841b1cb24d.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "ef6bccd06044f19f35357750f2d7ab06040a76545cf0a421f433997b7fd0e257", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "948fc9929716a13abd8a8c1a4f52d762607f5d394bd58d9f7e48c9c7b0c404e9", "generation_seconds_batch": 24.623479183996096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2695963382720947, "target_z": 1.2890623892397253, "ce": 6.1020402908325195, "genuineness": 4.607763767242432, "identity": 0.8048173785209656, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ef6bccd06044f19f35357750f2d7ab06040a76545cf0a421f433997b7fd0e257.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": "ef9d5ce67688c55e267c80d6690d7414c0f18dde21503a9a51d5b1a207e8c3c9", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "90010854c2cb1068a11fe79fd614ffac432e7dde0906b83412bab3c19f48c98d", "generation_seconds_batch": 20.393640883034095, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.224788635969162, "target_z": -0.20800781733742163, "ce": 6.0305562019348145, "genuineness": 4.3881025314331055, "identity": 0.6283577084541321, "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_Relief/ef9d5ce67688c55e267c80d6690d7414c0f18dde21503a9a51d5b1a207e8c3c9.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": "efdd9fab122b5c89d4e137f0e44c5fd55b2568078c36c646e04f44e2ad9d3898", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Someone moved the little blue chair.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can put it back after lunch.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Someone moved the little blue chair.\n(Natural clear speech.) [3.8 seconds duration] It used to stand here... beside the tall bookshelf.\n(Natural clear speech.) [3.2 seconds duration] We can put it back after lunch.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "859ec856b492dd9c4bfc47c17ae90c55f17c8e2469a9796373131834bdb7125e", "generation_seconds_batch": 16.006637098966166, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37745460867881775, "target_z": 0.010742177324733796, "ce": 6.419747352600098, "genuineness": 4.419482707977295, "identity": 0.3278436064720154, "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_Relief/efdd9fab122b5c89d4e137f0e44c5fd55b2568078c36c646e04f44e2ad9d3898.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "efed14b1fc4650be146ad392a6cb3b241333e84a47c6750bfc5a04cdd1d97ee6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "362f722d271077c573fd008227838aa54040678d0831ba09c1df62758fc80884", "generation_seconds_batch": 24.91507266892586, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5308021306991577, "target_z": 0.2304687413260026, "ce": 6.2767791748046875, "genuineness": 4.20609712600708, "identity": 0.20775291323661804, "hypothesis": "The 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_Relief/efed14b1fc4650be146ad392a6cb3b241333e84a47c6750bfc5a04cdd1d97ee6.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "f01788b95bf15edc627db505000753ba37b8f77df15b876de49638bda32a0e0d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "d0e9216286a975e616dc4449cb6f0e469b98c01ce9399c18e48b26f77d68b8a2", "generation_seconds_batch": 20.649259333964437, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2041680812835693, "target_z": 1.195312415928948, "ce": 6.086154937744141, "genuineness": 4.482243061065674, "identity": 0.6409795880317688, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f01788b95bf15edc627db505000753ba37b8f77df15b876de49638bda32a0e0d.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "f018a8e01bdbc3f9d03e61e1b55df64c6e6c7b845362e7264362b0b99221bdd8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "de84d2804c5d05d81eb33e8ca9adfc9f2bcdf643ffc17649f264d7d866597951", "generation_seconds_batch": 24.3242960650241, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8225032091140747, "target_z": 0.6484375146790725, "ce": 6.268836498260498, "genuineness": 4.796044826507568, "identity": 0.5750765800476074, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f018a8e01bdbc3f9d03e61e1b55df64c6e6c7b845362e7264362b0b99221bdd8.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": "f053cdc615914455651aa839d648ca1973d2cc3d0c572b224890c5b6c3a6c43c", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Jemand hat den kleinen blauen Stuhl umgestellt.\n(Natural clear speech.) [3.8 seconds duration] Er stand hier... neben dem hohen Bücherregal.\n(Natural clear speech.) [3.2 seconds duration] Wir stellen ihn nach dem Essen zurück.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "942ed29b15f1d7b816c8bd310254e6963e3f60d2b019d2252b6d68139cde0218", "generation_seconds_batch": 18.320680011995137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.36450526118278503, "target_z": -0.007812512010150274, "ce": 6.300607204437256, "genuineness": 4.375550270080566, "identity": 0.4881773591041565, "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_Relief/f053cdc615914455651aa839d648ca1973d2cc3d0c572b224890c5b6c3a6c43c.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "f0afc55b249771be5e554b45752a758cd72c25988c020650cf9390fd50e8e8bf", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "0c43ea2e4bf3154d6009f7fd890c092a4963e7ea783d4291dbbe42d815521d0b", "generation_seconds_batch": 30.001967835938558, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.39636749029159546, "target_z": 0.037841816349792286, "ce": 6.2767791748046875, "genuineness": 4.444586753845215, "identity": 0.4700521230697632, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f0afc55b249771be5e554b45752a758cd72c25988c020650cf9390fd50e8e8bf.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "f13b1ca5a06b30039697c258cba403b7b39964b3fe4c6191e708ff9daf030a28", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 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": "c8f82c6387111846c520e87c953dd430dc4b20460a775d332060176544ebb3ae", "generation_seconds_batch": 24.704380425973795, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7461702227592468, "target_z": 0.5390625173479948, "ce": 6.332377910614014, "genuineness": 4.061748504638672, "identity": 0.22191458940505981, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f13b1ca5a06b30039697c258cba403b7b39964b3fe4c6191e708ff9daf030a28.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "f181d43b266edbd0b4e8ec94be8989e84d6b5d176d899e5db1fc0eebb8644e6d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "4d7b888a2cc3d0bcca51ca835ae8006ea51669078776a8445def58603ecfc150", "generation_seconds_batch": 24.01444022997748, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 2.049283266067505, "target_z": 2.4062498558781966, "ce": 6.046441555023193, "genuineness": 4.143336772918701, "identity": 0.564670205116272, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble.", "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_Relief/f181d43b266edbd0b4e8ec94be8989e84d6b5d176d899e5db1fc0eebb8644e6d.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "f1a0bdf8671dffead18437ff152b1d74985fac9e3737068b784095ef84d14a40", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "cc843969beed67b673941e0864df90588bbf1532313f166995694aa4f89736c4", "generation_seconds_batch": 24.79009462101385, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.06189948320388794, "target_z": -0.44140626668076427, "ce": 5.982900142669678, "genuineness": 4.344170093536377, "identity": 0.6079105138778687, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f1a0bdf8671dffead18437ff152b1d74985fac9e3737068b784095ef84d14a40.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "f1a323b6c63b1935994957d6d58382c21330f800f91a5e79fc1e0dd5a4841feb", "bucket": "emo_Relief", "phase": "wording", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "24f71bc7791975db87d0a8522da4d849cc5b8ab6550d8244fd7ac0131b1e2794", "generation_seconds_batch": 18.08021842793096, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.767979621887207, "target_z": 0.5703124799830829, "ce": 6.419747352600098, "genuineness": 4.068024158477783, "identity": 0.5026305913925171, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f1a323b6c63b1935994957d6d58382c21330f800f91a5e79fc1e0dd5a4841feb.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": "f1cd065664bd1a7b5f8d421cc4a49386f13a78da50f4493af82d472c22bd1d29", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "080f70b19ecd78f7fdde0e756d732125bdec5ac3c4dd3940db387d056a8f6de9", "generation_seconds_batch": 25.353885357966647, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2799937427043915, "target_z": -0.12890625600507513, "ce": 6.443574905395508, "genuineness": 4.118232727050781, "identity": 0.20014771819114685, "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_Relief/f1cd065664bd1a7b5f8d421cc4a49386f13a78da50f4493af82d472c22bd1d29.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "f1d268bba9bd622b33a20e2bdae036a8ae7bd3ef20659fb1f5e93aa11f1a11c8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "297797aad3d881df5501c48b20b5e9ab683a9be3159b270560672c85ae823369", "generation_seconds_batch": 24.48612298700027, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7243608236312866, "target_z": 0.5078125547129068, "ce": 6.205295085906982, "genuineness": 4.325342178344727, "identity": 0.5019307732582092, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. ¿Podemos mirar juntos lo que hay dentro?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f1d268bba9bd622b33a20e2bdae036a8ae7bd3ef20659fb1f5e93aa11f1a11c8.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "46a59596da3fe475422c99d5a0062ad736362a8cbd1932263b75bf8f704be045", "generation_seconds_batch": 17.07953952299431, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6616586446762085, "target_z": 0.4179686879475569, "ce": 6.221180438995361, "genuineness": 4.632867813110352, "identity": 0.7505221962928772, "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_Relief/f21bc0adf2df6aeda4aa5bc68657c60b57559ffed3b647118e970ebfd0ba6ad8.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "f2822af71a253e1e7f67a8a4a6f3371c0d0b455d6c9d5a65faf61aa8028af24e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "a36d868f75ab8fab2cc82b4912c5b61af32fc247c107e2e22252ecd153c8723f", "generation_seconds_batch": 16.684013176942244, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.38767778873443604, "target_z": 0.025390632005920993, "ce": 6.252951145172119, "genuineness": 4.595211505889893, "identity": 0.6747807264328003, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f2822af71a253e1e7f67a8a4a6f3371c0d0b455d6c9d5a65faf61aa8028af24e.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "f282e06c08ec17e0c69386f67c5fb0e0570f658c12190e119c59c3467e946074", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "ac4267a92f4193a05282f56fb930b236729ca13595779c1f696c293fb3490aad", "generation_seconds_batch": 19.16009701602161, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2641440629959106, "target_z": 1.2812500053378446, "ce": 6.229123115539551, "genuineness": 4.369274139404297, "identity": 0.4942282736301422, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f282e06c08ec17e0c69386f67c5fb0e0570f658c12190e119c59c3467e946074.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": "f33649b10660622bbf226f55c6382c2e3d8ca9a74781129e3f25349eb1ba94e5", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Neem ze mee als je weggaat.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De sleutels liggen op de keukentafel.\n(Natural clear speech.) [3.8 seconds duration] Ik keek in de la... en daarna naast het raam.\n(Natural clear speech.) [3.2 seconds duration] Neem ze mee als je weggaat.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3a79dcd456c45e302bf2a9424b9e98d782faa1cba2bc3feaa99005da4ca8496b", "generation_seconds_batch": 16.62069625291042, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6153136491775513, "target_z": 0.35156248532092743, "ce": 6.117925643920898, "genuineness": 4.444586753845215, "identity": 0.3509650230407715, "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_Relief/f33649b10660622bbf226f55c6382c2e3d8ca9a74781129e3f25349eb1ba94e5.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "f359111ceb7142857f41d48bc32324afe84ca0feda108b597319fda0a0e242d8", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "e24674f0baa19718187faab89b302ce3542f4160785791fea7a35cdf82ab5240", "generation_seconds_batch": 25.052806542022154, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5757840871810913, "target_z": 0.2949218906799184, "ce": 6.221180438995361, "genuineness": 4.457139015197754, "identity": 0.8286871910095215, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f359111ceb7142857f41d48bc32324afe84ca0feda108b597319fda0a0e242d8.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "f36043e9248e220f43a61fbf72758af2fb7a0d691bd5ee6f190594c7b1fab9c9", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "a42ebb1a7aa3fe94198ead06596d43341ef88a7704a7d90c8e0becb8b6e883c3", "generation_seconds_batch": 23.973733845050447, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.20229767262935638, "target_z": -0.2402343706630013, "ce": 6.1020402908325195, "genuineness": 4.507347106933594, "identity": 0.5400168299674988, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f36043e9248e220f43a61fbf72758af2fb7a0d691bd5ee6f190594c7b1fab9c9.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "f3c065d0f0d00808adfc7e745a5f07ca32cee63b12de9876425fc926609c259e", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "17e03c495c8c9aa4a4257e3dcb7cedc76d052f902971af8d65482047afc77cd2", "generation_seconds_batch": 15.923540688934736, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7080037593841553, "target_z": 0.4843750613852125, "ce": 6.459460258483887, "genuineness": 4.293961524963379, "identity": 0.5412452220916748, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f3c065d0f0d00808adfc7e745a5f07ca32cee63b12de9876425fc926609c259e.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "f3c513fc484fe2772682474038098b481ee0c27f29bebcd921e4e6f73343febe", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": 127, "seconds_generated": 10.16, "mp3_sha256": "6ef5c5c01c5b4160d668863c2b6b58fb6e8b383c8cbb8b04968e1a8fc8d141e0", "generation_seconds_batch": 25.583574846968986, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.24455343186855316, "target_z": -0.17968749866553885, "ce": 6.173524379730225, "genuineness": 4.268857479095459, "identity": 0.42476773262023926, "hypothesis": "De deur 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_Relief/f3c513fc484fe2772682474038098b481ee0c27f29bebcd921e4e6f73343febe.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "f3df284191864d33c8df36d87ed109d25714584346b00c1e51da5007b0c49d80", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "25ce337bf854e4fa5b5c47e84893c6057a02d9760f6c7cd69272ea045d4f4c03", "generation_seconds_batch": 23.734034743043594, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.43197816610336304, "target_z": 0.08886716931796694, "ce": 6.268836498260498, "genuineness": 4.356721878051758, "identity": 0.4914184808731079, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f3df284191864d33c8df36d87ed109d25714584346b00c1e51da5007b0c49d80.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": "f3df45f96eea7436cfae8e5cb34390b4e078440335356492dda50ff75bab432f", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Ich warte auf der anderen Seite.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Natural clear speech.) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Natural clear speech.) [3.2 seconds duration] Ich warte auf der anderen Seite.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "742b96a120f8255608ba8321341e2160441be4b2a7e31a9a9ab757b698b366d1", "generation_seconds_batch": 17.923446572036482, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4708262085914612, "target_z": 0.14453123732261916, "ce": 6.324435234069824, "genuineness": 4.595211505889893, "identity": 0.4346974492073059, "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_Relief/f3df45f96eea7436cfae8e5cb34390b4e078440335356492dda50ff75bab432f.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "f466afa5c499a9e2399bdc42d95ea9f4a3e299fa3b2fbb56c1c318f49fcde291", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "seed": 1701, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "99b4299365875919d3dbb9e9424c310e3588ab68081ba1d8b02627194ffc2986", "generation_seconds_batch": 24.673941436922178, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.18866677582263947, "target_z": -0.2597656293369987, "ce": 5.9431867599487305, "genuineness": 4.193545341491699, "identity": 0.4994683861732483, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f466afa5c499a9e2399bdc42d95ea9f4a3e299fa3b2fbb56c1c318f49fcde291.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "f4a060139c1b460513d5116d2299faaf398e9416bf1801f4e1e0e3df0a42587d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5515d314396a5801e97e249750a7bacddfd48bbd550decd9f57a2e60bef0524d", "generation_seconds_batch": 27.94715218199417, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3941524624824524, "target_z": 0.03466797667336303, "ce": 6.308549880981445, "genuineness": 4.469690799713135, "identity": 0.5174196362495422, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f4a060139c1b460513d5116d2299faaf398e9416bf1801f4e1e0e3df0a42587d.mp3" }, { "id": "emo_Relief-nl-0", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar wanneer je klaar bent." ], "text": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-0", "key": "f5081fa20c5b923d681f196035114b171f16d5c6083404ab904a345bb18a6473", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] De deur staat nog open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik heb je jas op de stoel gelegd.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer je klaar bent.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] De deur staat nog open.\n(Natural clear speech.) [3.8 seconds 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": "f9c6ba7b6ec04677e92a1fa7e73a0a25ecd622a741429589d67d2269fb64d227", "generation_seconds_batch": 26.69957619009074, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.17367279529571533, "target_z": -0.28125000533784456, "ce": 6.149696350097656, "genuineness": 4.250029563903809, "identity": 0.6870371103286743, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f5081fa20c5b923d681f196035114b171f16d5c6083404ab904a345bb18a6473.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "f542ba64a18df4e518f4f9063a6d2423e7d77d34016d892f58944e0bf74df44a", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": 127, "seconds_generated": 10.16, "mp3_sha256": "021827bdcfd0b08004c27697c31a5a332346ed964b637e6c65ac40e83f1419b8", "generation_seconds_batch": 21.935717694927007, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.351381778717041, "target_z": 1.4062500266892228, "ce": 6.09409761428833, "genuineness": 4.469690799713135, "identity": 0.7404354214668274, "hypothesis": "J'ai trouvé la 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_Relief/f542ba64a18df4e518f4f9063a6d2423e7d77d34016d892f58944e0bf74df44a.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "f58444c98720d8e3e49f7645aa54817fcb1f324d1332ae863a34568107e9cca3", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.75, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "686ba122a5a702a484f2ab6916cfa9d95f9a64ba8ec82ae080884b46c36dba92", "generation_seconds_batch": 32.156592471990734, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9915262460708618, "target_z": 0.8906250026689223, "ce": 6.117925643920898, "genuineness": 4.055472373962402, "identity": 0.34527358412742615, "hypothesis": "The 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_Relief/f58444c98720d8e3e49f7645aa54817fcb1f324d1332ae863a34568107e9cca3.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "f5cb6290a7a83c283316331633180be6ac6c130b6c181124da353574fbca0eba", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "eab68029faeaff1724e35ec17d3ce6bf05f614c3650d0ec7ab14b7bfe6f4dccf", "generation_seconds_batch": 25.608992620022036, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.46673694252967834, "target_z": 0.1386718639906956, "ce": 6.149696350097656, "genuineness": 4.143336772918701, "identity": 0.4603525996208191, "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_Relief/f5cb6290a7a83c283316331633180be6ac6c130b6c181124da353574fbca0eba.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "f5fdccb33a529a629ccc76b034f91b37916645483d667c4b8a36c280156bcc4f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7f650d534ff660eb6d6405d2ea4088b33e4ffb3abbd68d5095383a9b2694fec0", "generation_seconds_batch": 16.234699595952407, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7979675531387329, "target_z": 0.613281189282018, "ce": 6.2767791748046875, "genuineness": 4.281409740447998, "identity": 0.5916377305984497, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f5fdccb33a529a629ccc76b034f91b37916645483d667c4b8a36c280156bcc4f.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "f6094c92cc9888745231599d21a07406b52bd7fac05bad79bf0fc5baa0f12c50", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "8619acaec46bf7e5cf6e0dbbd88865a1ae4444cdd637235ce9088577d5c07747", "generation_seconds_batch": 23.355500111938454, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.351381778717041, "target_z": 1.4062500266892228, "ce": 6.24500846862793, "genuineness": 4.532451152801514, "identity": 0.5951630473136902, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. We've regarded ensemble what it contiens?", "wer": 0.3157894736842105, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f6094c92cc9888745231599d21a07406b52bd7fac05bad79bf0fc5baa0f12c50.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": "f61766544bb1a805e50db0df8458b8a35b5c91b64a0289c9d50dfce2a07b55ff", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The keys are on the kitchen table.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I checked the drawer... then looked beside the window.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "e1e7f674331bbe4799ef6291b176bbec0f0dcd385bbe828ea39e67bd268c9918", "generation_seconds_batch": 24.41706253204029, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7352654933929443, "target_z": 0.5234374933276943, "ce": 6.443574905395508, "genuineness": 4.406930446624756, "identity": 0.2905886173248291, "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_Relief/f61766544bb1a805e50db0df8458b8a35b5c91b64a0289c9d50dfce2a07b55ff.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "f66eace9d370596c8e8e8ef26aef2aa7e8d6b1dd1446aac956b3ab1697800a14", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "e36f7b9ae079aa9dd7cfe724685464be6600cb08f66fac6e8a84fa9a28fccf55", "generation_seconds_batch": 24.258117060060613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4422013461589813, "target_z": 0.10351562399915415, "ce": 6.133810997009277, "genuineness": 4.507347106933594, "identity": 0.5564439296722412, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f66eace9d370596c8e8e8ef26aef2aa7e8d6b1dd1446aac956b3ab1697800a14.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "f69ab3d5c636096c38ab3a54d06b46849193cd94d872d7efea59d4a586360eca", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1702, "scale": 1.0, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "4297677c818091a69f0a7ff91483af9013e5fce0b6cb75d8eadfda9ff5f75845", "generation_seconds_batch": 25.051892729010433, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6725634336471558, "target_z": 0.4335937973733705, "ce": 5.863759994506836, "genuineness": 3.8922953605651855, "identity": 0.5334405899047852, "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_Relief/f69ab3d5c636096c38ab3a54d06b46849193cd94d872d7efea59d4a586360eca.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "f6cf285844c5a6cd9ead38a25b337ffb7325f339eaec72aea4e2d59837c6fbc6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "9a0b0ae195a0a50ca1b721e0576947b4971951cb2100d69faaadeded6cfd66f5", "generation_seconds_batch": 17.1578430730151, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9588121175765991, "target_z": 0.8437500160135337, "ce": 6.292664527893066, "genuineness": 3.948779582977295, "identity": 0.29411154985427856, "hypothesis": "The 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_Relief/f6cf285844c5a6cd9ead38a25b337ffb7325f339eaec72aea4e2d59837c6fbc6.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "f741e73d53c2f4a5506eae20a601516b02970b07e4f1ee704dd1ae374378b877", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "351c3ab1ae9d9f14eb683d508e770cc1333b94cfffd919148c708e4600b82230", "generation_seconds_batch": 26.892150399042293, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3622864484786987, "target_z": 1.4218749653040104, "ce": 6.300607204437256, "genuineness": 4.319066047668457, "identity": 0.6038984060287476, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f741e73d53c2f4a5506eae20a601516b02970b07e4f1ee704dd1ae374378b877.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "f75528bec2ef8e8320f224cad6f66f82cbac1165426a5c39c88a561b52ee9723", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "ca8da329e996a348cc56ca35c009de0b0cd78e552040aa691d10124d38ce48c3", "generation_seconds_batch": 22.550550703075714, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.9838550090789795, "target_z": 2.3124998825674195, "ce": 6.149696350097656, "genuineness": 4.256305694580078, "identity": 0.6995974779129028, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble what 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_Relief/f75528bec2ef8e8320f224cad6f66f82cbac1165426a5c39c88a561b52ee9723.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "f75aef8b3020ef55748773baf2b609fd28531029c9ca74c372dcef8f631aecb9", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1701, "scale": 0.75, "cfg": 2.5, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "bed5be5d7abbfda9bdbc706b372a2cd7da38a41ad3c23a70a42d1cde4b953964", "generation_seconds_batch": 21.07569629396312, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0787639617919922, "target_z": 1.0156250240203006, "ce": 6.213237762451172, "genuineness": 4.457139015197754, "identity": 0.6865454912185669, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt?", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f75aef8b3020ef55748773baf2b609fd28531029c9ca74c372dcef8f631aecb9.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "8f04ae772427bf86d3ba2a1a0750a8d0b364375837420f02e6b29ff1d13af58d", "generation_seconds_batch": 18.73381980904378, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.26499977707862854, "target_z": -0.15039061065454273, "ce": 6.165581703186035, "genuineness": 4.519899368286133, "identity": 0.6847366094589233, "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_Relief/f7a65885d0e107603bdce9d92b5fc3b68a68524db7b0b06f79b6538794e8bf5c.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "f7b28656d77212d1ca1f97234d1963efcb98260e78e1b7c0267cb24e19d385ca", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "e99ea434ac7d8d2c74b741c9db1654cf22d692413238c558ebbe0dbf96414305", "generation_seconds_batch": 24.54998477094341, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.1005733013153076, "target_z": 1.0468749012498755, "ce": 6.165581703186035, "genuineness": 4.1998209953308105, "identity": 0.388277530670166, "hypothesis": "I found the little box. It was beside the old window. We can look inside together,", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f7b28656d77212d1ca1f97234d1963efcb98260e78e1b7c0267cb24e19d385ca.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "f7cc765edc57d6e8b6bf459819080a969be544c7fc6772f0f0a4c772dd027030", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "cef814a2e6ec6f110e8eb8f71a28d2ba09ab5a20bf7809fc72347634425ec962", "generation_seconds_batch": 21.916149997967295, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.630307674407959, "target_z": 0.3730469253759081, "ce": 6.292664527893066, "genuineness": 3.9676074981689453, "identity": 0.432003915309906, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f7cc765edc57d6e8b6bf459819080a969be544c7fc6772f0f0a4c772dd027030.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": "f8161180f15803b80ef66c26b51a21c2f6824f278dba63113bb956095f1b718b", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a9be75ab97806dff98c0d7f9bc44adc681ec2d83f8f111c2bc8e08f05ab612fa", "generation_seconds_batch": 22.213161524035968, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8006937503814697, "target_z": 0.6171874666384715, "ce": 6.284721851348877, "genuineness": 4.532451152801514, "identity": 0.7688816785812378, "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_Relief/f8161180f15803b80ef66c26b51a21c2f6824f278dba63113bb956095f1b718b.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_Relief", "phase": "heldout", "candidate": "standard", "prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": "17084fd0baf5642d5106f1f0116fc9afd0d96230560a9298492c11804ccd4b5b", "generation_seconds_batch": 17.189651445951313, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.27590447664260864, "target_z": -0.1347656293369987, "ce": 6.316492557525635, "genuineness": 4.582659721374512, "identity": 0.6527544260025024, "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_Relief/f86feddc7af334e5c3d6691e715ece3168f8e7618bd3b63ca7d0171f412fdf9d.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "f8a01ef88abce9df20ae24a49de528d3d0baaa3c1ef7f09ceec9c418c122311b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": "f4169a93672a53ef57ea96862715f8ddc8449893bc3bbdb92caf888b8b48aa39", "generation_seconds_batch": 27.075846263905987, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.789789080619812, "target_z": 0.6015625280236839, "ce": 6.109982967376709, "genuineness": 4.18726921081543, "identity": 0.6354564428329468, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f8a01ef88abce9df20ae24a49de528d3d0baaa3c1ef7f09ceec9c418c122311b.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "f8c1076da5ab3efbc3cb476ce64eca5b3f61dd92fdc3a3138cc207b61245ff97", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1702, "scale": 0.5, "cfg": 3.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "300fe3f1d58dbc5b56b7472030beecf352a313f4db0a831bf12a084ba82fd917", "generation_seconds_batch": 24.990794991026632, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7093667984008789, "target_z": 0.48632811465792614, "ce": 6.133810997009277, "genuineness": 3.8420867919921875, "identity": 0.2375393658876419, "hypothesis": "The 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_Relief/f8c1076da5ab3efbc3cb476ce64eca5b3f61dd92fdc3a3138cc207b61245ff97.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": "f8d1aebf9966b90f2513a31667ff958fd8a54f11a5dfaf6d656f9dc0cbf93741", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich schrieb die Nummer auf den Umschlag.\n(Natural clear speech.) [3.8 seconds duration] Lies sie genau... und prüfe die letzten beiden Ziffern.\n(Natural clear speech.) [3.2 seconds duration] Ruf an, wenn du Zeit hast.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7363265b37a10a14bfa00fe2fe988277cc9ee9068b63dc86f9aabcf5ed331bd0", "generation_seconds_batch": 18.615383217926137, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.392789363861084, "target_z": 0.032714837995136324, "ce": 6.427689552307129, "genuineness": 4.381826400756836, "identity": 0.4411725103855133, "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_Relief/f8d1aebf9966b90f2513a31667ff958fd8a54f11a5dfaf6d656f9dc0cbf93741.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "f9372c2c04f03a9e36c39ad19a2770e0c24a39db939524906412d59c4e7fa81d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "c590522c0f022287cdcb011b6b215a0f51065917b1224bc566e885c56f5cf53c", "generation_seconds_batch": 22.04779015108943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2586917877197266, "target_z": 1.273437621435964, "ce": 5.9431867599487305, "genuineness": 4.105680465698242, "identity": 0.2264283001422882, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/f9372c2c04f03a9e36c39ad19a2770e0c24a39db939524906412d59c4e7fa81d.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": "f995ca30933134718b7ecac39a8fba5022bc84b066352778d3daf8d44e2544ae", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Llévatelas cuando te vayas.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Las llaves están en la mesa de la cocina.\n(Natural clear speech.) [3.8 seconds duration] Miré en el cajón... y luego junto a la ventana.\n(Natural clear speech.) [3.2 seconds duration] Llévatelas cuando te vayas.", "seed": 1701, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "1b69539a397263e9a6928db34d982e7c282ac771de011a31690806f099681728", "generation_seconds_batch": 17.537423270987347, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8906576633453369, "target_z": 0.7460937653463031, "ce": 6.284721851348877, "genuineness": 4.381826400756836, "identity": 0.5847475528717041, "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_Relief/f995ca30933134718b7ecac39a8fba5022bc84b066352778d3daf8d44e2544ae.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": "f99f44fe30e98b503c5a95e3889832eb2c535e3b3ace9dd8547fcceb5dd2e011", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Te esperaré al otro lado.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La carretera gira a la izquierda tras el puente.\n(Natural clear speech.) [3.8 seconds duration] Sigue... hasta la pequeña puerta de madera.\n(Natural clear speech.) [3.2 seconds duration] Te esperaré al otro lado.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "71e96ed1b44a4d502e2cdcdfc746869adb5a05e025773b78bedc2242d2dcb504", "generation_seconds_batch": 17.447530281031504, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.23160408437252045, "target_z": -0.19824218800042293, "ce": 6.149696350097656, "genuineness": 4.632867813110352, "identity": 0.5281241536140442, "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_Relief/f99f44fe30e98b503c5a95e3889832eb2c535e3b3ace9dd8547fcceb5dd2e011.mp3" }, { "id": "emo_Relief-en-0", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell me when you are ready." ], "text": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-0", "key": "f9c1bc179b39e56810eacfea556b2693b6a41a79b55130d72c3722a1750f7661", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The door is still open.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] I put your coat on the chair.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Tell me when you are ready.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The door is still open.\n(Natural clear speech.) [3.8 seconds duration] I put your coat on the chair.\n(Natural clear speech.) [3.2 seconds duration] Tell me when you are ready.", "seed": 1701, "scale": 0.5, "cfg": 1.5, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "45afc30e6eb0449aa21029cd5d83d39f0d00868e0f92699cb6c4a20bf4fe6a75", "generation_seconds_batch": 31.657955243019387, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6616586446762085, "target_z": 0.4179686879475569, "ce": 6.324435234069824, "genuineness": 4.13078498840332, "identity": 0.3867254853248596, "hypothesis": "The 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_Relief/f9c1bc179b39e56810eacfea556b2693b6a41a79b55130d72c3722a1750f7661.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "fa0b8a95fa3e6609cfbf581421b60e2b3594bf8f025286a41cfdfb1b967342d1", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": "a92a46829db824a3d15e649783aaddc324626b94ddd4930af15c3946f40e890f", "generation_seconds_batch": 19.27401447307784, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.138739824295044, "target_z": 1.101562442618171, "ce": 6.372091293334961, "genuineness": 4.306513786315918, "identity": 0.49844080209732056, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/fa0b8a95fa3e6609cfbf581421b60e2b3594bf8f025286a41cfdfb1b967342d1.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "fa0f9066b66f174ff43415b296c4d20be42476cfc7a64cc29a682be17cf82705", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Natural clear speech.) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "a1cb04f3dae0ba7da45779d1ad857cc330d7320166b8d46a19a8ae49a32c9f19", "generation_seconds_batch": 19.735312632052228, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.45719534158706665, "target_z": 0.12500002135137828, "ce": 6.38003396987915, "genuineness": 4.482243061065674, "identity": 0.5402556657791138, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/fa0f9066b66f174ff43415b296c4d20be42476cfc7a64cc29a682be17cf82705.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "fa11405a6409075ff3e7056dbc985434252a2b0b7b489849a09e097467fbd10f", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "fe156334c6496d26158f31167faa019aa57f3c3584e7827cc1276caff5d56526", "generation_seconds_batch": 23.97468792705331, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.8688482046127319, "target_z": 0.7148437173057021, "ce": 6.324435234069824, "genuineness": 3.911123275756836, "identity": 0.5189917087554932, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/fa11405a6409075ff3e7056dbc985434252a2b0b7b489849a09e097467fbd10f.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "faa04ebf35e4470b4ccd13821bec2b8347cbf2d5ada94ce1a55026fdd982dcd4", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "5631a6bb18d35afe17a78ecdf45b28d07af30ec0b9d8d4cf06051cb5fcae65d0", "generation_seconds_batch": 24.258117060060613, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3038477897644043, "target_z": -0.09472658535264705, "ce": 6.213237762451172, "genuineness": 4.432034492492676, "identity": 0.5994263291358948, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/faa04ebf35e4470b4ccd13821bec2b8347cbf2d5ada94ce1a55026fdd982dcd4.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "facc27c65e733fac8d278fdd1f40725c10283af1451fbf5f612126ad71ea4529", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [3.8 seconds duration] It was beside the old window.\n(Natural clear speech.) [3.2 seconds duration] We can look inside together.", "seed": 1701, "scale": 0.75, "cfg": 5.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "6dc4ef041b9ca65d4aeb380b2a4706befe0f301211361679aeb37eb27f96562a", "generation_seconds_batch": 22.04779015108943, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.231429934501648, "target_z": 1.234375018682456, "ce": 6.062326908111572, "genuineness": 4.093128204345703, "identity": 0.3107248544692993, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/facc27c65e733fac8d278fdd1f40725c10283af1451fbf5f612126ad71ea4529.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": "fad0dbce2ce4af06a86fd11a5b2628df942c7e2f6fac0fa4f7537492cc41a8ac", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Prends-les quand tu partiras.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Les clés sont sur la table de la cuisine.\n(Natural clear speech.) [3.8 seconds duration] J’ai regardé dans le tiroir... puis près de la fenêtre.\n(Natural clear speech.) [3.2 seconds duration] Prends-les quand tu partiras.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 127, "seconds_generated": 10.16, "mp3_sha256": "7b8c7839fd30c97b0833d202f901c3e0068e6766b1f7ef5315659951996d9f44", "generation_seconds_batch": 19.07860932603944, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7325392961502075, "target_z": 0.5195312159712409, "ce": 6.109982967376709, "genuineness": 4.243753433227539, "identity": 0.6912792921066284, "hypothesis": "Les clés sont sur la table de la cuisine. J'ai regardé dans le tiroir, puis près de la fenêtre. Prends les quand tu partiras.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/fad0dbce2ce4af06a86fd11a5b2628df942c7e2f6fac0fa4f7537492cc41a8ac.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": "fb112f22cc3e905e245a20776d27e6248469a98f2790581b428fac6fd1949ee7", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] The road turns left behind the bridge.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] I will meet you on the other side.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] The road turns left behind the bridge.\n(Natural clear speech.) [3.8 seconds duration] Keep going... until you reach the small wooden gate.\n(Natural clear speech.) [3.2 seconds duration] I will meet you on the other side.", "seed": 1702, "scale": 0.0, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "ac959eb499981239ebd3141b149c918174b9b798e6e3c1fef176288f0eda8699", "generation_seconds_batch": 16.223765004076995, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5880519151687622, "target_z": 0.31250005337844566, "ce": 6.427689552307129, "genuineness": 4.055472373962402, "identity": 0.25821754336357117, "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_Relief/fb112f22cc3e905e245a20776d27e6248469a98f2790581b428fac6fd1949ee7.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": "fb257eca8aa6cdb5f193caf8c7c9c5995068bf01ef9acbf097d6030d7d79992b", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Escribí el número en el sobre.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Llámame cuando tengas un momento.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Escribí el número en el sobre.\n(Natural clear speech.) [3.8 seconds duration] Léelo bien... y comprueba las dos últimas cifras.\n(Natural clear speech.) [3.2 seconds duration] Llámame cuando tengas un momento.", "seed": 1702, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "3d6a5f04ab035f6b882c626dc54237a665d7f4f9d0592a62463d15931af07216", "generation_seconds_batch": 20.300306031946093, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.0296926498413086, "target_z": 0.9453123732261915, "ce": 6.23706579208374, "genuineness": 3.9927117824554443, "identity": 0.49134716391563416, "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_Relief/fb257eca8aa6cdb5f193caf8c7c9c5995068bf01ef9acbf097d6030d7d79992b.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": "fc1653021482a3087c5ec3029029c991a2186f0255b6decf26756b95cdb5ff61", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Straße führt hinter der Brücke nach links.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Geh weiter... bis zu dem kleinen Holztor.\n(Ensure the final word carries a lingering, warm resonance) [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": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "7f52a516e4a2fe97f4dff53132460b69cee90bdf7599c41f77d7310a73863950", "generation_seconds_batch": 25.39212818793021, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.9015623927116394, "target_z": 0.7617187893666036, "ce": 6.292664527893066, "genuineness": 4.3504462242126465, "identity": 0.44628506898880005, "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_Relief/fc1653021482a3087c5ec3029029c991a2186f0255b6decf26756b95cdb5ff61.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "fc78dc40b8752a071d189d4fdef9710bdd66a6c78a988ef5092bb7a88cbf3eb0", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "264479db15bf76b42999d16701881e06e8eae6ac82174325f3c637f035717fbb", "generation_seconds_batch": 25.097826470038854, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.37813615798950195, "target_z": 0.011718746663847146, "ce": 6.046441555023193, "genuineness": 4.331617832183838, "identity": 0.5907515287399292, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/fc78dc40b8752a071d189d4fdef9710bdd66a6c78a988ef5092bb7a88cbf3eb0.mp3" }, { "id": "emo_Relief-en-1", "language": "en", "sentences": [ "I found the little box.", "It was beside the old window.", "We can look inside together." ], "text": "I found the little box. It was beside the old window. We can look inside together.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-en-1", "key": "fcabbca7953ca48e754d34df543231f53dc73e210cea9a167dd2080933088ce6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] I found the little box.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] It was beside the old window.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We can look inside together.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] I found the little box.\n(Natural clear speech.) [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": 127, "seconds_generated": 10.16, "mp3_sha256": "e0374469cf679c2ba4dfe6a60470af0f7dec2f3418e8211d7528880a0493e7cc", "generation_seconds_batch": 29.114267172990367, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.2750487327575684, "target_z": 1.2968749439526321, "ce": 6.268836498260498, "genuineness": 4.262581825256348, "identity": 0.37337493896484375, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/fcabbca7953ca48e754d34df543231f53dc73e210cea9a167dd2080933088ce6.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "fccdd98d8babe82b50071fd311a4899049652cf3c4d5181a8a4c9ce37446be20", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": 129, "seconds_generated": 10.32, "mp3_sha256": "2803def68d297bc1380a9aa7db12279a5bf1df90fb15ffad9c7f320a56480001", "generation_seconds_batch": 23.282256457023323, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.44697216153144836, "target_z": 0.11035156667019107, "ce": 6.268836498260498, "genuineness": 4.457139015197754, "identity": 0.635820746421814, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.120000000000001, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/fccdd98d8babe82b50071fd311a4899049652cf3c4d5181a8a4c9ce37446be20.mp3" }, { "id": "emo_Relief-es-1", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos mirar juntos lo que hay dentro." ], "text": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-1", "key": "fce9d727a1980fa1930d58a675e0a2f183e43643110616b12922b63cb59a7a77", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] He encontrado la cajita.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Estaba junto a la ventana vieja.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Podemos mirar juntos lo que hay dentro.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] He encontrado la cajita.\n(Natural clear speech.) [3.8 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": 127, "seconds_generated": 10.16, "mp3_sha256": "12fec0c0b2ac02ef09062ccacf2db6e1970f22d0e1464cb39522d801fa49eef9", "generation_seconds_batch": 24.3242960650241, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.5785102844238281, "target_z": 0.2988281680363718, "ce": 6.1894097328186035, "genuineness": 4.482243061065674, "identity": 0.633979082107544, "hypothesis": "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_Relief/fce9d727a1980fa1930d58a675e0a2f183e43643110616b12922b63cb59a7a77.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "fd44adf241d9e082d3dbf505fcdd778ce8c41864d4e9686285a9188b40e59fda", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 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": "41826839d3924f6438e95bd2df82c1074927768328b929a6e0430dea92da26cd", "generation_seconds_batch": 23.790454932954162, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3968786299228668, "target_z": 0.0385742113270599, "ce": 6.205295085906982, "genuineness": 4.582659721374512, "identity": 0.4826289117336273, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/fd44adf241d9e082d3dbf505fcdd778ce8c41864d4e9686285a9188b40e59fda.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": "fd53f539fd552b355491d824ee0e9e903c7297f6acf2ac71d7d27f2febcff0c2", "bucket": "emo_Relief", "phase": "heldout", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Je bericht kwam nadat ik vertrokken was.\n(Natural clear speech.) [3.8 seconds duration] Ik las het twee keer... en legde mijn telefoon weg.\n(Natural clear speech.) [3.2 seconds duration] Zeg maar wanneer we kunnen praten.", "seed": 1701, "scale": 0.0, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "5c62618bb4adc20ebc6fdb8a5e901962ccadd11e3aae4a5002c61b9d6a7b1fb0", "generation_seconds_batch": 19.763028072891757, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7516225576400757, "target_z": 0.5468749866553886, "ce": 6.308549880981445, "genuineness": 4.607763767242432, "identity": 0.5503570437431335, "hypothesis": "Je beri kwam nadat ik vertrokken was. Ik las het twee keer en legde mijn telefoon weg. Zeg maar wanneer we kunnen praten.", "wer": 0.043478260869565216, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/fd53f539fd552b355491d824ee0e9e903c7297f6acf2ac71d7d27f2febcff0c2.mp3" }, { "id": "emo_Relief-de-1", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben dem alten Fenster.", "Wir können gemeinsam hineinschauen." ], "text": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-1", "key": "fe88e3bc322c11d02a73be0febc689a89f69fad9fdc88957e486d365fee28c4b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Sie stand neben dem alten Fenster.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Wir können gemeinsam hineinschauen.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ich habe die kleine Schachtel gefunden.\n(Natural clear 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": "bde87e55eb067dfcef26ec58cacaed4ee7908065a8cabf1ced14df0869039287", "generation_seconds_batch": 32.30301510996651, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4640107750892639, "target_z": 0.1347656293369987, "ce": 6.435632705688477, "genuineness": 4.369274139404297, "identity": 0.5059748888015747, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/fe88e3bc322c11d02a73be0febc689a89f69fad9fdc88957e486d365fee28c4b.mp3" }, { "id": "emo_Relief-nl-1", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We kunnen er samen in kijken." ], "text": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-nl-1", "key": "feb4e7fa80dedc1f6c081a2655f892e1ff2f2b526824038c4e1fd60a64661244", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Het stond naast het oude raam.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] We kunnen er samen in kijken.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Ik heb het kleine doosje gevonden.\n(Natural clear speech.) [3.8 seconds duration] Het stond naast het oude raam.\n(Natural clear speech.) [3.2 seconds duration] We kunnen er samen in kijken.", "seed": 1702, "scale": 0.5, "cfg": 5.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "76e9737b8e22943b15e5392b01e6de40f1fcb9a0aaec8e4da2414381c646eaf4", "generation_seconds_batch": 24.06204975291621, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.2929430902004242, "target_z": -0.11035156667019107, "ce": 5.998785495758057, "genuineness": 4.287685871124268, "identity": 0.5031680464744568, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/feb4e7fa80dedc1f6c081a2655f892e1ff2f2b526824038c4e1fd60a64661244.mp3" }, { "id": "emo_Relief-de-0", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, wenn du bereit bist." ], "text": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-de-0", "key": "fec753bb558a4d95fa7e3e4ac88b02d855cb51bdb9173789c7ffa209f6fbea7b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] Die Tür ist noch offen.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Ich habe deinen Mantel auf den Stuhl gelegt.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Sag mir, wenn du bereit bist.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] Die Tür ist noch offen.\n(Natural clear speech.) [3.8 seconds 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": "67d25628ca0ccba74e27dc8ccf759f0d16b7a2e6286d6624d411d493d69fe660", "generation_seconds_batch": 24.889950006036088, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.3828217685222626, "target_z": 0.0184326021539612, "ce": 6.173524379730225, "genuineness": 4.250029563903809, "identity": 0.5849862098693848, "hypothesis": "Die Tür ist noch offen, ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/fec753bb558a4d95fa7e3e4ac88b02d855cb51bdb9173789c7ffa209f6fbea7b.mp3" }, { "id": "emo_Relief-fr-1", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’elle contient." ], "text": "J’ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu’elle contient.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-1", "key": "fee0787a50a08c7acc4d692adafdfe32ff0659518750a1380fef038ebcbc080b", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] Elle était près de la vieille fenêtre.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Nous pouvons regarder ensemble ce qu’elle contient.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] J’ai trouvé la petite boîte.\n(Natural clear speech.) [3.8 seconds duration] 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": "9a6150b807aa19f849bff1d6cbe6aceed9a7227905d091fc1a7043c334934cc0", "generation_seconds_batch": 21.91708782291971, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 1.3350247144699097, "target_z": 1.3828125333615287, "ce": 6.221180438995361, "genuineness": 4.281409740447998, "identity": 0.432958722114563, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/fee0787a50a08c7acc4d692adafdfe32ff0659518750a1380fef038ebcbc080b.mp3" }, { "id": "emo_Relief-fr-0", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi quand tu es prêt." ], "text": "La porte est encore ouverte. J’ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-fr-0", "key": "ff4dffefb05e66a523442cd529614a43dede7ef3f896b1345818eb866c65535d", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La porte est encore ouverte.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dis-moi quand tu es prêt.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La porte est encore ouverte.\n(Natural clear speech.) [3.8 seconds duration] J’ai posé ton manteau sur la chaise.\n(Natural clear speech.) [3.2 seconds duration] Dis-moi quand tu es prêt.", "seed": 1702, "scale": 0.5, "cfg": 4.0, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "af74e5cb53079c0187564ce4ce590647bcd8fcc3734c86cff2cc61b09b18c047", "generation_seconds_batch": 23.260567906079814, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.6016827821731567, "target_z": 0.3320312693496866, "ce": 6.054384231567383, "genuineness": 4.494794845581055, "identity": 0.8978297710418701, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/manual-comparison-v1/audio/emo_Relief/ff4dffefb05e66a523442cd529614a43dede7ef3f896b1345818eb866c65535d.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "ff7dd4ce05b5b5f7b43d72daaabd7ac0b31af0e946e341e66165d9402e8af8fb", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [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": "832a21c5b70ba05b67ea541b671d24f44b1b9392afd64a3f47d00b2f15b36d27", "generation_seconds_batch": 25.54912859702017, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.7761582136154175, "target_z": 0.5820313120524431, "ce": 6.046441555023193, "genuineness": 4.118232727050781, "identity": 0.683181881904602, "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_Relief/ff7dd4ce05b5b5f7b43d72daaabd7ac0b31af0e946e341e66165d9402e8af8fb.mp3" }, { "id": "emo_Relief-es-0", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu abrigo sobre la silla.", "Dime cuándo estás listo." ], "text": "La puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "sentence_seconds": [ 3.2, 3.8, 3.2 ], "seconds": 10.2, "frames": 128, "max_frames": 188, "reference": true, "task_id": "emo_Relief-es-0", "key": "ffe1c73c95fd7344b5f6d01692b0daac25058e4fe6ccf9468c166de7a74a18d6", "bucket": "emo_Relief", "phase": "grid", "candidate": "manual-c17f294b7963", "prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects. Shift the resonance forward slightly, giving the relief a bright, almost stunned quality without becoming overly bright.\nSCRIPT:\n(Project the sound from a relaxed throat space) [3.2 seconds duration] La puerta sigue abierta.\n(Introduce a gentle upward inflection on the key words) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Ensure the final word carries a lingering, warm resonance) [3.2 seconds duration] Dime cuándo estás listo.", "neutral_prompt": "GENERAL: One adult speaker, clean high-quality recording, no music or sound effects.\nSCRIPT:\n(Natural clear speech.) [3.2 seconds duration] La puerta sigue abierta.\n(Natural clear speech.) [3.8 seconds duration] He dejado tu abrigo sobre la silla.\n(Natural clear speech.) [3.2 seconds duration] Dime cuándo estás listo.", "seed": 1701, "scale": 0.0, "cfg": 1.25, "ended": true, "frames_generated": 128, "seconds_generated": 10.24, "mp3_sha256": "123b2baf308e7297f8387e4949c0d007ec56398c33e3dfece49ed4b823b8f994", "generation_seconds_batch": 16.928226470947266, "original_audio_reused": false, "scoring_contract": "singleton-EARS-ASR-Orange128-preMP3-v1", "metrics": { "valid_waveform": true, "target_raw": 0.4830940365791321, "target_z": 0.1621094000211464, "ce": 5.998785495758057, "genuineness": 3.9550557136535645, "identity": 0.5500533580780029, "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_Relief/ffe1c73c95fd7344b5f6d01692b0daac25058e4fe6ccf9468c166de7a74a18d6.mp3" }, { "key": "original-emo_Relief-de-0-seed1701-scale0.0", "bucket": "emo_Relief", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "8a64904f6194d41649069463005ff96f3f131c48bf1bf40f33b9c81dc4cffb2b", "task_id": "emo_Relief-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.17912515997886658, "target_z": -0.2734374933276943, "ce": 6.260893821716309, "genuineness": 4.406930446624756, "identity": 0.5952259302139282, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/211b0362fa985b49eee03c76.mp3" }, { "key": "original-emo_Relief-de-0-seed1701-scale0.5", "bucket": "emo_Relief", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "c9edecae3d2b19b2a8c42c31458a285cc44b513fba7b9efba6f6f5501e4aa6c3", "task_id": "emo_Relief-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.2363748997449875, "target_z": -0.191406245329386, "ce": 6.086154937744141, "genuineness": 4.607763767242432, "identity": 0.541637659072876, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/e96544aa1655127ae583a20d.mp3" }, { "key": "original-emo_Relief-de-0-seed1701-scale0.75", "bucket": "emo_Relief", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "d2441d7b3a8b6004ffaa3127fea1b49e08a8422dad660a9e919e6e655820949b", "task_id": "emo_Relief-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.22069936990737915, "target_z": -0.2138671906693452, "ce": 6.165581703186035, "genuineness": 4.7458367347717285, "identity": 0.6005347371101379, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/01f87ce06ae281e4193c9103.mp3" }, { "key": "original-emo_Relief-de-0-seed1701-scale1.0", "bucket": "emo_Relief", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "3b54c848489b52f5ac9610081c8c33e53c0395b1acbcc19f24c0159ce63a3086", "task_id": "emo_Relief-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.20843157172203064, "target_z": -0.23144531066511592, "ce": 6.308549880981445, "genuineness": 4.369274139404297, "identity": 0.582379162311554, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/6cb104e9ceadf3148d635853.mp3" }, { "key": "original-emo_Relief-de-0-seed1702-scale0.0", "bucket": "emo_Relief", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "ab926079d77ecbeed82deee2bb2345aa99d33e0fe3747e32d75056b717950f17", "task_id": "emo_Relief-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.22001782059669495, "target_z": -0.21484376000845856, "ce": 6.141753673553467, "genuineness": 4.457139015197754, "identity": 0.6220689415931702, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/5b73f16a74fc273c93682a34.mp3" }, { "key": "original-emo_Relief-de-0-seed1702-scale0.5", "bucket": "emo_Relief", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "60cec847a6905ed1d29ee6a0a47e5045cf19a4e3d08e65f0413623c332360069", "task_id": "emo_Relief-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.2513688802719116, "target_z": -0.16992186932854014, "ce": 6.260893821716309, "genuineness": 4.796044826507568, "identity": 0.7077821493148804, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/5982506084cf1c7ec8fc0a50.mp3" }, { "key": "original-emo_Relief-de-0-seed1702-scale0.75", "bucket": "emo_Relief", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "0df5c801c6d9ad55c5e7fc53fb0334b020316f60bc71ba0fc484d6e2922cf2ef", "task_id": "emo_Relief-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.19957149028778076, "target_z": -0.24414062666807643, "ce": 6.268836498260498, "genuineness": 4.532451152801514, "identity": 0.4482881724834442, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/26044227c6f1017946befddc.mp3" }, { "key": "original-emo_Relief-de-0-seed1702-scale1.0", "bucket": "emo_Relief", "language": "de", "sentences": [ "Die Tür ist noch offen.", "Ich habe deinen Mantel auf den Stuhl gelegt.", "Sag mir, 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "04384e160e341fa54ba755fc893d7527485365e4a4e76bb853f197ec400af987", "task_id": "emo_Relief-de-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.17367279529571533, "target_z": -0.28125000533784456, "ce": 6.221180438995361, "genuineness": 4.293961524963379, "identity": 0.567592442035675, "hypothesis": "Die Tür ist noch offen. Ich habe deinen Mantel auf den Stuhl gelegt. Sag mir, wenn du bereit bist.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/526abd742bcc9a5e9a1e8ded.mp3" }, { "key": "original-emo_Relief-de-1-seed1701-scale0.0", "bucket": "emo_Relief", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "c31b706f207fea99fb97d890066b9bd8413a0ddc44f7e1f289bea1b966a9d411", "task_id": "emo_Relief-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.48990947008132935, "target_z": 0.17187500800676686, "ce": 6.38003396987915, "genuineness": 4.293961524963379, "identity": 0.662719190120697, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/743bb2b63bf31094a61837ca.mp3" }, { "key": "original-emo_Relief-de-1-seed1701-scale0.5", "bucket": "emo_Relief", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "8c5492fb4436df4e737858a2a434cd26dd1d83327ff85c68a08562d0efe2642a", "task_id": "emo_Relief-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.6521170735359192, "target_z": 0.4042968880109961, "ce": 6.332377910614014, "genuineness": 4.325342178344727, "identity": 0.4573841989040375, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/30b10e9a41a6b785939cf877.mp3" }, { "key": "original-emo_Relief-de-1-seed1701-scale0.75", "bucket": "emo_Relief", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "b9ecc1baf541b2cb8a5ba6c22b7b79029c44e65db59bc7dff9dd9320d7847905", "task_id": "emo_Relief-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.5553377270698547, "target_z": 0.26562498131754403, "ce": 6.515059471130371, "genuineness": 4.3127899169921875, "identity": 0.36705321073532104, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/cbac32e4dceb181bb2fd179e.mp3" }, { "key": "original-emo_Relief-de-1-seed1701-scale1.0", "bucket": "emo_Relief", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "aae5c8b6c2f46e9ab9443a27f15e21bce6c63b41af8c1656947e38761cd33cf1", "task_id": "emo_Relief-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.6125874519348145, "target_z": 0.34765620796447405, "ce": 6.38797664642334, "genuineness": 4.331617832183838, "identity": 0.5184181928634644, "hypothesis": "Ich habe die kleine Schachtel gefunden, sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/213ff1f408856312665feb13.mp3" }, { "key": "original-emo_Relief-de-1-seed1702-scale0.0", "bucket": "emo_Relief", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "1598c2e715fa6aac73ef825797367104643396482fe0cc868c417a5f0291f2b1", "task_id": "emo_Relief-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.38179945945739746, "target_z": 0.016967769496669442, "ce": 6.443574905395508, "genuineness": 4.042920112609863, "identity": 0.4163440465927124, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/d85b3f890ff73144197de36d.mp3" }, { "key": "original-emo_Relief-de-1-seed1702-scale0.5", "bucket": "emo_Relief", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "7882e9e66daaedcf45f7fe13f0de34c39811699b4b7390b64ff56e6eff893c4c", "task_id": "emo_Relief-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.4031829237937927, "target_z": 0.04760742433541273, "ce": 6.427689552307129, "genuineness": 4.337893962860107, "identity": 0.6136902570724487, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/474480fd5991123db7a5464e.mp3" }, { "key": "original-emo_Relief-de-1-seed1702-scale0.75", "bucket": "emo_Relief", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "477c62ed1bcc18b0ab2ad31956d66d4cbd07e6947f7e0c7d7d23c6caf28730fa", "task_id": "emo_Relief-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.3474666476249695, "target_z": -0.032226574676957914, "ce": 6.38003396987915, "genuineness": 4.337893962860107, "identity": 0.4913536608219147, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/9cb3d0ef604b8dc253004241.mp3" }, { "key": "original-emo_Relief-de-1-seed1702-scale1.0", "bucket": "emo_Relief", "language": "de", "sentences": [ "Ich habe die kleine Schachtel gefunden.", "Sie stand neben 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "00e42c60db51ae4d17925b5b562287f964c3e9f9abbcead7ed5d9ad69834c4d4", "task_id": "emo_Relief-de-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.363142192363739, "target_z": -0.009765607985620445, "ce": 6.372091293334961, "genuineness": 4.494794845581055, "identity": 0.5193812847137451, "hypothesis": "Ich habe die kleine Schachtel gefunden. Sie stand neben dem alten Fenster. Wir können gemeinsam hineinschauen.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/de/6cfb9bc2f08f3c6e94678ac0.mp3" }, { "key": "original-emo_Relief-en-0-seed1701-scale0.0", "bucket": "emo_Relief", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "6982c774269a06a09726aeba084b44eeccb4d151bf3a849382442cd1277ae115", "task_id": "emo_Relief-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.3481481969356537, "target_z": -0.03125000533784457, "ce": 6.260893821716309, "genuineness": 4.3881025314331055, "identity": 0.4304714798927307, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/bc7e4f4e1d2f005f8fce2ebe.mp3" }, { "key": "original-emo_Relief-en-0-seed1701-scale0.5", "bucket": "emo_Relief", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "00a36d9fef5939bc2f95a2d13ad4bda16f0e3273519a4cfc0cf7c8b7bb25f5e1", "task_id": "emo_Relief-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.449016809463501, "target_z": 0.11328127468753112, "ce": 6.205295085906982, "genuineness": 4.162164688110352, "identity": 0.2655458450317383, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/7b8eb0ceaf01f7fdde33646b.mp3" }, { "key": "original-emo_Relief-en-0-seed1701-scale0.75", "bucket": "emo_Relief", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "88983797056cfd3d7329b42a5c45a768ac5b53ecc82a7cb129be6f3ca613acb6", "task_id": "emo_Relief-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.36859452724456787, "target_z": -0.0019531386782267015, "ce": 6.133810997009277, "genuineness": 3.8922953605651855, "identity": 0.4793233871459961, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/7cb92c131b710b6d44d03897.mp3" }, { "key": "original-emo_Relief-en-0-seed1701-scale1.0", "bucket": "emo_Relief", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "1b74e6dd93010d16081fbd8863daee56bcc0784a4c772596c26b69f93af8e553", "task_id": "emo_Relief-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.42141422629356384, "target_z": 0.07373045131860134, "ce": 6.133810997009277, "genuineness": 3.773050308227539, "identity": 0.29085773229599, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/3aa1e2fdfd936b7fc9617566.mp3" }, { "key": "original-emo_Relief-en-0-seed1702-scale0.0", "bucket": "emo_Relief", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "2d234c864af6571fa29a42c0ed96438ec61f0f5b2aaa52f4a923e456bdc71a85", "task_id": "emo_Relief-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.49195408821105957, "target_z": 0.17480467332135036, "ce": 6.308549880981445, "genuineness": 4.293961524963379, "identity": 0.2622988522052765, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/67d5dc01b42d10d295c2d50d.mp3" }, { "key": "original-emo_Relief-en-0-seed1702-scale0.5", "bucket": "emo_Relief", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "d74cfa80b35ca6fee2efc8187c23d188555e25840826ac16acaa1e6a9143f9ce", "task_id": "emo_Relief-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.694372832775116, "target_z": 0.46484376000845856, "ce": 6.229123115539551, "genuineness": 3.998987913131714, "identity": 0.2606217861175537, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/320f41ec545292397265df8d.mp3" }, { "key": "original-emo_Relief-en-0-seed1702-scale0.75", "bucket": "emo_Relief", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "9eaf00dbb9bb2edd54a5af439b31ef93d38fa6ff758f9e1be9ddb4ee8ed1859b", "task_id": "emo_Relief-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.48036783933639526, "target_z": 0.158203122664693, "ce": 6.006728172302246, "genuineness": 3.7918784618377686, "identity": 0.539162278175354, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/c583a946fb3425684e1098bc.mp3" }, { "key": "original-emo_Relief-en-0-seed1702-scale1.0", "bucket": "emo_Relief", "language": "en", "sentences": [ "The door is still open.", "I put your coat on the chair.", "Tell 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "7e3116856cc4d5e5787fd4b0b05812b9f2af7fe58a0aae9251ed3e2c90ad69f5", "task_id": "emo_Relief-en-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.4486760199069977, "target_z": 0.11279296866659617, "ce": 6.133810997009277, "genuineness": 3.8420867919921875, "identity": 0.3261941075325012, "hypothesis": "The door is still open. I put your coat on the chair. Tell me when you are ready.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/2fbedadbb79cd1c42016097d.mp3" }, { "key": "original-emo_Relief-en-1-seed1701-scale0.0", "bucket": "emo_Relief", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "5922eef7156c55482b0d7d16754fcbf4cd1e2adc7ac493eb748954dc9e6ce708", "task_id": "emo_Relief-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.6003196835517883, "target_z": 0.33007813067145986, "ce": 6.38797664642334, "genuineness": 4.68307638168335, "identity": 0.34269559383392334, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/004b10db2c1ee4abc2d67c95.mp3" }, { "key": "original-emo_Relief-en-1-seed1701-scale0.5", "bucket": "emo_Relief", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "c056ef0a5089390b22fbeea8b196148ff7bc7c94e0ff9510a744c589dbc7895f", "task_id": "emo_Relief-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.9370026588439941, "target_z": 0.8124999679729326, "ce": 6.41180419921875, "genuineness": 4.356721878051758, "identity": 0.4079138934612274, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/2d9ca649e85f4a553a6708c8.mp3" }, { "key": "original-emo_Relief-en-1-seed1701-scale0.75", "bucket": "emo_Relief", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "f2bcea323ca880ef2f0ea5c4f745f17d007b659eb9769d35993a59a3f807006a", "task_id": "emo_Relief-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 1.1005733013153076, "target_z": 1.0468749012498755, "ce": 6.443574905395508, "genuineness": 4.532451152801514, "identity": 0.34256163239479065, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/6f6bbcd05fda932d6d04a5ae.mp3" }, { "key": "original-emo_Relief-en-1-seed1701-scale1.0", "bucket": "emo_Relief", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "d0a6e4be8d833a9e08b619de9c218c2604a71a5969dc5e02f12dfbe9cca2d053", "task_id": "emo_Relief-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.8225032091140747, "target_z": 0.6484375146790725, "ce": 6.356205940246582, "genuineness": 4.545003414154053, "identity": 0.5526280403137207, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/cb6ab737550d8c036657a054.mp3" }, { "key": "original-emo_Relief-en-1-seed1702-scale0.0", "bucket": "emo_Relief", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "4917fd00a90aa5da48982142dc08e939e05874bd1818e232dc74ec3784678911", "task_id": "emo_Relief-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.8661220073699951, "target_z": 0.7109374399492486, "ce": 6.395919322967529, "genuineness": 4.381826400756836, "identity": 0.40142032504081726, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/fd8b4aeaa0261894c981df35.mp3" }, { "key": "original-emo_Relief-en-1-seed1702-scale0.5", "bucket": "emo_Relief", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "ff485ec4da6a2cb98c4f02d01e05aeb14991ea808e1bebed5a50d5614128e228", "task_id": "emo_Relief-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 1.0569545030593872, "target_z": 0.9843749759796995, "ce": 6.348263263702393, "genuineness": 4.519899368286133, "identity": 0.361105352640152, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/78419fb89027292a8e1a6ca8.mp3" }, { "key": "original-emo_Relief-en-1-seed1702-scale0.75", "bucket": "emo_Relief", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "5c3d467b7c81e142283441f35c2d1674bdef4dcb5c852d49867c04427b3ea7bc", "task_id": "emo_Relief-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 1.059680700302124, "target_z": 0.9882812533361529, "ce": 6.4515180587768555, "genuineness": 4.645420074462891, "identity": 0.3253304660320282, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/dffc0b3561547e1b72d210ac.mp3" }, { "key": "original-emo_Relief-en-1-seed1702-scale1.0", "bucket": "emo_Relief", "language": "en", "sentences": [ "I found the little box.", "It was beside the 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "07d323073b6416be3022e183500adf981a1ddc565e267f31b98ed45b00ea8e6d", "task_id": "emo_Relief-en-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.9533597230911255, "target_z": 0.8359374613006268, "ce": 6.332377910614014, "genuineness": 4.394378662109375, "identity": 0.34204787015914917, "hypothesis": "I found the little box. It was beside the old window. We can look inside together.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/en/b4f935c1f2c9c1901ce64ab2.mp3" }, { "key": "original-emo_Relief-es-0-seed1701-scale0.0", "bucket": "emo_Relief", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "8228f0659d5b8c3e149d28a40f122e673be1c19d3c45e97d1f6832043255c425", "task_id": "emo_Relief-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.4275481402873993, "target_z": 0.08251953266786496, "ce": 6.252951145172119, "genuineness": 4.507347106933594, "identity": 0.5971918106079102, "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_Relief/es/3113c006b04e1a04383f5e2e.mp3" }, { "key": "original-emo_Relief-es-0-seed1701-scale0.5", "bucket": "emo_Relief", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "cfdf3618573a02778b8e4968b7bf16dbc51c110e3ca5685cd3cb548598555378", "task_id": "emo_Relief-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.35530441999435425, "target_z": -0.02099609133128918, "ce": 6.109982967376709, "genuineness": 4.13078498840332, "identity": 0.5122461318969727, "hypothesis": "la puerta sigue abierta. He dejado tu abrigo sobre la silla. Dime cuándo estás listo.", "wer": 0.0, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/es/642b5961ea95b3c2296da1a5.mp3" }, { "key": "original-emo_Relief-es-0-seed1701-scale0.75", "bucket": "emo_Relief", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "e25e0ea2fd3801aec0f60baf67d19b1aeb71603b0ea7372cf2bc8db1bb81af13", "task_id": "emo_Relief-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.4050571620464325, "target_z": 0.05029295799090704, "ce": 6.157639026641846, "genuineness": 3.9676074981689453, "identity": 0.5023481845855713, "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_Relief/es/7e2e11a14cf2b5b3fe7362c2.mp3" }, { "key": "original-emo_Relief-es-0-seed1701-scale1.0", "bucket": "emo_Relief", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "e22d4287e44252b8483671725b7629aaaa4722baeae41bb382e9f4a6a4434f45", "task_id": "emo_Relief-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.4742339253425598, "target_z": 0.14941404131542937, "ce": 6.109982967376709, "genuineness": 4.193545341491699, "identity": 0.4328184723854065, "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_Relief/es/663b04dfc3d972e2ce6054ea.mp3" }, { "key": "original-emo_Relief-es-0-seed1702-scale0.0", "bucket": "emo_Relief", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "9ff99ae9e3f666d8b27823fab829116436fceac6bc802be235f5488cce667c9e", "task_id": "emo_Relief-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.2602289617061615, "target_z": -0.15722655332557964, "ce": 6.109982967376709, "genuineness": 4.457139015197754, "identity": 0.5358825325965881, "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_Relief/es/6664ef5781904391b15fbff3.mp3" }, { "key": "original-emo_Relief-es-0-seed1702-scale0.5", "bucket": "emo_Relief", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "6934a621bde271b2c0293e0fa998fc8484bd38b4fa45fefe6fd7a2b2f1fcf362", "task_id": "emo_Relief-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.42311811447143555, "target_z": 0.07617189601776297, "ce": 6.173524379730225, "genuineness": 4.055472373962402, "identity": 0.5699790716171265, "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_Relief/es/24238455fd21fbe79366e05b.mp3" }, { "key": "original-emo_Relief-es-0-seed1702-scale0.75", "bucket": "emo_Relief", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "881294f955da4253053d280cf385e7c06ea9c29caec4cbd20fa0084cdaab4f72", "task_id": "emo_Relief-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.3849515914916992, "target_z": 0.02148435464946759, "ce": 6.0146708488464355, "genuineness": 4.093128204345703, "identity": 0.5349277257919312, "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_Relief/es/f8c874ff78667005fb184a5b.mp3" }, { "key": "original-emo_Relief-es-0-seed1702-scale1.0", "bucket": "emo_Relief", "language": "es", "sentences": [ "La puerta sigue abierta.", "He dejado tu 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "419b3df970e4f66db338572b702e050955975bd97df234c573c104fad73446ab", "task_id": "emo_Relief-es-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.18730369210243225, "target_z": -0.26171874666384715, "ce": 5.919358730316162, "genuineness": 4.086852550506592, "identity": 0.6916095018386841, "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_Relief/es/f581c82426c2e73d0e23ea59.mp3" }, { "key": "original-emo_Relief-es-1-seed1701-scale0.0", "bucket": "emo_Relief", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "35e1f63598c11d61ffdae7f8c0aa94db6fce058a0a97d6dc1b7855509bc8be04", "task_id": "emo_Relief-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.8115984797477722, "target_z": 0.632812490658772, "ce": 6.3641486167907715, "genuineness": 4.7834930419921875, "identity": 0.6216393709182739, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/es/ee1bb832a5fd1a7fe987d796.mp3" }, { "key": "original-emo_Relief-es-1-seed1701-scale0.5", "bucket": "emo_Relief", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "054270ab988b8435d1be0823d14c17d849b66caa61c128698dd8a39455dd4f78", "task_id": "emo_Relief-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.7107298970222473, "target_z": 0.48828125333615285, "ce": 6.141753673553467, "genuineness": 4.532451152801514, "identity": 0.6304444670677185, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/es/57be0d8179529a5d628a6751.mp3" }, { "key": "original-emo_Relief-es-1-seed1701-scale0.75", "bucket": "emo_Relief", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "07c6a2161e634a92a382f4e67732cba7dd2b0b68e1178543a953b5031029fb8b", "task_id": "emo_Relief-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.4851386547088623, "target_z": 0.16503906533572993, "ce": 6.300607204437256, "genuineness": 4.582659721374512, "identity": 0.530178964138031, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/es/2e11ab75ca9f765aef00c85e.mp3" }, { "key": "original-emo_Relief-es-1-seed1701-scale1.0", "bucket": "emo_Relief", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "8c0a956628126ddd8ea6692f26ab249243a5ac5e11fa47a0d1629a6673ad8e34", "task_id": "emo_Relief-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.46810004115104675, "target_z": 0.14062500266892228, "ce": 5.95112943649292, "genuineness": 4.419482707977295, "identity": 0.5618293285369873, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/es/421ac99821805b56422a29f3.mp3" }, { "key": "original-emo_Relief-es-1-seed1702-scale0.0", "bucket": "emo_Relief", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "11694f97a9eb6eeb5c81961ff2adcb34000d0e62154334bab73f8de58e5ed102", "task_id": "emo_Relief-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.47900474071502686, "target_z": 0.1562499839864663, "ce": 6.0305562019348145, "genuineness": 4.720732688903809, "identity": 0.7613346576690674, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/es/c19552d00c5d0c72a357e5af.mp3" }, { "key": "original-emo_Relief-es-1-seed1702-scale0.5", "bucket": "emo_Relief", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "2d517129e4c7d88faf7e6b9eaf7cd4785dd4d0127ca5826cac64e58de74f62b3", "task_id": "emo_Relief-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.5239866971969604, "target_z": 0.22070313334038213, "ce": 6.109982967376709, "genuineness": 4.432034492492676, "identity": 0.6679741144180298, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/es/ab3d88c2e6c06b33f0b61482.mp3" }, { "key": "original-emo_Relief-es-1-seed1702-scale0.75", "bucket": "emo_Relief", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "bfc21730df69eaafa9d13ed0dbf18e0b4c667a73322e750d5630379534431046", "task_id": "emo_Relief-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.39176705479621887, "target_z": 0.03125000533784457, "ce": 6.1020402908325195, "genuineness": 4.645420074462891, "identity": 0.6956584453582764, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/es/7f7365dc1277f956218cf801.mp3" }, { "key": "original-emo_Relief-es-1-seed1702-scale1.0", "bucket": "emo_Relief", "language": "es", "sentences": [ "He encontrado la cajita.", "Estaba junto a la ventana vieja.", "Podemos 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "35b5eec805795ab238d46a2de51c98d7f827c4e7af161daf1b0e73251bebb3e8", "task_id": "emo_Relief-es-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.2275148183107376, "target_z": -0.2041015613323465, "ce": 5.982900142669678, "genuineness": 4.432034492492676, "identity": 0.42745858430862427, "hypothesis": "He encontrado la cajita. Estaba junto a la ventana vieja. Podemos mirar juntos lo que hay dentro.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/es/7ad9d631a67ab602b3e19377.mp3" }, { "key": "original-emo_Relief-fr-0-seed1701-scale0.0", "bucket": "emo_Relief", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "363204c861b6e7e6561b8a9545031853bc20104195be719109d5d53b6d69f389", "task_id": "emo_Relief-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.3420143127441406, "target_z": -0.04003904398435166, "ce": 5.982900142669678, "genuineness": 4.356721878051758, "identity": 0.8211699724197388, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu y es prêt.", "wer": 0.05555555555555555, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/405ad7caec471a0fda64d9ca.mp3" }, { "key": "original-emo_Relief-fr-0-seed1701-scale0.5", "bucket": "emo_Relief", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "1be83abc2d22ea70f3616816bde9ca6e4104add782372e0850156cd2a2aa0af3", "task_id": "emo_Relief-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.5239866971969604, "target_z": 0.22070313334038213, "ce": 6.1020402908325195, "genuineness": 4.444586753845215, "identity": 0.8648278713226318, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/f70949b6ae8764fd74ea854d.mp3" }, { "key": "original-emo_Relief-fr-0-seed1701-scale0.75", "bucket": "emo_Relief", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "5feda58ec55e70b201dfa810368aa89ae4a820eebb4c73df785c609d8499d065", "task_id": "emo_Relief-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.42243656516075134, "target_z": 0.07519532667864963, "ce": 6.133810997009277, "genuineness": 4.432034492492676, "identity": 0.7469329833984375, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/a36b250c90a0dee231b764f6.mp3" }, { "key": "original-emo_Relief-fr-0-seed1701-scale1.0", "bucket": "emo_Relief", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "8784ac67536e7c871f7e47859d12fa8855126bafa5affc39e3c9a24d44f05258", "task_id": "emo_Relief-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.33042803406715393, "target_z": -0.05664063734376556, "ce": 6.0146708488464355, "genuineness": 4.218649387359619, "identity": 0.6493350267410278, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/aced19cefbc61401043fd32c.mp3" }, { "key": "original-emo_Relief-fr-0-seed1702-scale0.0", "bucket": "emo_Relief", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "fb24301401faf9059c362b2964f1ca92206979a4eff42a445637656b3f4ea29f", "task_id": "emo_Relief-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.25273197889328003, "target_z": -0.16796873065031345, "ce": 6.141753673553467, "genuineness": 4.369274139404297, "identity": 0.6484242677688599, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/e0e12d16e7fee624c3898bcb.mp3" }, { "key": "original-emo_Relief-fr-0-seed1702-scale0.5", "bucket": "emo_Relief", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "77577e72aa65dbf4a75073f854e21697aa020f40d59659c4b82e76dcc0ea5b6e", "task_id": "emo_Relief-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.3501928448677063, "target_z": -0.028320297320504513, "ce": 6.1894097328186035, "genuineness": 4.507347106933594, "identity": 0.6465277671813965, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/35a390b4ac8ee8c74dddfc21.mp3" }, { "key": "original-emo_Relief-fr-0-seed1702-scale0.75", "bucket": "emo_Relief", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "69508b559525d9c3841f7fda143669a5dffe263911938158818d10c2f0f12ee2", "task_id": "emo_Relief-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.6289445161819458, "target_z": 0.37109370129216834, "ce": 6.2767791748046875, "genuineness": 4.507347106933594, "identity": 0.7333316802978516, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/12b254d76c58bd94b8d6bd85.mp3" }, { "key": "original-emo_Relief-fr-0-seed1702-scale1.0", "bucket": "emo_Relief", "language": "fr", "sentences": [ "La porte est encore ouverte.", "J’ai posé ton manteau sur la chaise.", "Dis-moi 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "7f8be8b7ed8e64f5c9faac32e2a71c5dd3396fb55545bfaccc8f8fe25cb39f9b", "task_id": "emo_Relief-fr-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.630307674407959, "target_z": 0.3730469253759081, "ce": 6.205295085906982, "genuineness": 4.532451152801514, "identity": 0.7576883435249329, "hypothesis": "La porte est encore ouverte. J'ai posé ton manteau sur la chaise. Dis-moi quand tu es prêt.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/d7a7ab98efaecfca2ac37ab9.mp3" }, { "key": "original-emo_Relief-fr-1-seed1701-scale0.0", "bucket": "emo_Relief", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "9677df9f56e0e68d71a4a4c4f2a9d9aca6a6bcd1549cbf2b84178ad11397780c", "task_id": "emo_Relief-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 1.0787639617919922, "target_z": 1.0156250240203006, "ce": 6.078212261199951, "genuineness": 4.6203155517578125, "identity": 0.6455376148223877, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/ed0a231fa7f58b37cfbe938d.mp3" }, { "key": "original-emo_Relief-fr-1-seed1701-scale0.5", "bucket": "emo_Relief", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "85cb6c2b9a8e76e95d16233bc9ea30ef9897cd536611b3ec5619ea6068b80199", "task_id": "emo_Relief-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 1.0215141773223877, "target_z": 0.9335937119678575, "ce": 5.967014789581299, "genuineness": 4.218649387359619, "identity": 0.7071948647499084, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/5d825bb2b538320b34b8c0ec.mp3" }, { "key": "original-emo_Relief-fr-1-seed1701-scale0.75", "bucket": "emo_Relief", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "fb3d30c695cd48fd10881ad5da0ff79e65c9607f66ced03e87c882f8b6571144", "task_id": "emo_Relief-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 1.4059052467346191, "target_z": 1.4843748905741865, "ce": 6.284721851348877, "genuineness": 4.507347106933594, "identity": 0.6966950297355652, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/30aa7c5283e66190c0de7101.mp3" }, { "key": "original-emo_Relief-fr-1-seed1701-scale1.0", "bucket": "emo_Relief", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "2d16c127fd415a265c72effc89b32f4dcefc5cf5d678292c29ecf69ec26bf3cc", "task_id": "emo_Relief-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.6589325070381165, "target_z": 0.4140624959966166, "ce": 6.054384231567383, "genuineness": 4.607763767242432, "identity": 0.48499178886413574, "hypothesis": "J'ai trouvé la 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/audio/emo_Relief/fr/1ddb70fff8093bca85706d1d.mp3" }, { "key": "original-emo_Relief-fr-1-seed1702-scale0.0", "bucket": "emo_Relief", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "e85a1a5c2abee420545850e9398a5508a02081841c660cda5837b5cbddda472c", "task_id": "emo_Relief-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.7298130989074707, "target_z": 0.5156249386147875, "ce": 5.967014789581299, "genuineness": 4.457139015197754, "identity": 0.7750236988067627, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/cef56c152731572919204fed.mp3" }, { "key": "original-emo_Relief-fr-1-seed1702-scale0.5", "bucket": "emo_Relief", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "dd7b17fb3e34e146f47d7f81f3a8f370af089fe9e82f7b9cb7c55eaba8b40ba0", "task_id": "emo_Relief-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 1.1005733013153076, "target_z": 1.0468749012498755, "ce": 6.221180438995361, "genuineness": 4.582659721374512, "identity": 0.8561403751373291, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/0bce7764a36dc955415daecd.mp3" }, { "key": "original-emo_Relief-fr-1-seed1702-scale0.75", "bucket": "emo_Relief", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "95c6491f6885692ef0662764739f2841a2ccb3f0735161eec5884293d9772d9d", "task_id": "emo_Relief-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.9588121175765991, "target_z": 0.8437500160135337, "ce": 6.046441555023193, "genuineness": 4.369274139404297, "identity": 0.8020929098129272, "hypothesis": "J'ai trouvé la petite boîte. Elle y 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/audio/emo_Relief/fr/c083e83d45d317db6c010cb8.mp3" }, { "key": "original-emo_Relief-fr-1-seed1702-scale1.0", "bucket": "emo_Relief", "language": "fr", "sentences": [ "J’ai trouvé la petite boîte.", "Elle était près de la vieille fenêtre.", "Nous pouvons regarder ensemble ce qu’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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "852cbc764cdc6d7b85d775ba0e5276064168c143c3273bf7ffa286fb501ef2ec", "task_id": "emo_Relief-fr-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.7080037593841553, "target_z": 0.4843750613852125, "ce": 5.839932441711426, "genuineness": 4.545003414154053, "identity": 0.803005576133728, "hypothesis": "J'ai trouvé la petite boîte. Elle était près de la vieille fenêtre. Nous pouvons regarder ensemble ce qu'elle contient.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/fr/b47295a6a8cf62537c386d52.mp3" }, { "key": "original-emo_Relief-nl-0-seed1701-scale0.0", "bucket": "emo_Relief", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 0.5, 0.75, 1.0 ], "cfg": 1.0, "reference": true, "case_type": "Neutral wording, target emotion/style varies only through acoustic performance", "seed": 1701, "scale": 0.0, "frames_generated": 127, "seconds_generated": 10.16, "ended": true, "contract_sha256": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "50552da805d1d4bca31bb273877da73f7021879caf8a0dec94dd1dd2d1e8d663", "task_id": "emo_Relief-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.11505997180938721, "target_z": -0.3652343706630013, "ce": 6.046441555023193, "genuineness": 4.306513786315918, "identity": 0.6243860125541687, "hypothesis": "De deuren staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.05263157894736842, "duration_error_s": 0.03999999999999915, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/2d11cb770d5d9f8ba5b40e64.mp3" }, { "key": "original-emo_Relief-nl-0-seed1701-scale0.5", "bucket": "emo_Relief", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "6252bde9590ab152af7fbb703b8efe789d28541915aea06df3fd679c0dbe6f4c", "task_id": "emo_Relief-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.09052437543869019, "target_z": -0.40039061065454273, "ce": 6.086154937744141, "genuineness": 4.250029563903809, "identity": 0.6025207042694092, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/55555a226f635499c90cf837.mp3" }, { "key": "original-emo_Relief-nl-0-seed1701-scale0.75", "bucket": "emo_Relief", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "ef0d72c62464b8fb5001d4dfd24e8c9bdfa9e75c45fb89fa7567652d8f58080e", "task_id": "emo_Relief-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.19548222422599792, "target_z": -0.25, "ce": 6.1020402908325195, "genuineness": 4.2249250411987305, "identity": 0.5706642866134644, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/5214ed7c71f710eb7a4ad28c.mp3" }, { "key": "original-emo_Relief-nl-0-seed1701-scale1.0", "bucket": "emo_Relief", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "eba9fe14a867a1ac772663e84362d8d27a12f4b1823650e3ff278f64345d64f4", "task_id": "emo_Relief-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.09325054287910461, "target_z": -0.39648437600084585, "ce": 6.038498878479004, "genuineness": 4.256305694580078, "identity": 0.500104546546936, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/1f23c5c7aebf9101654f9273.mp3" }, { "key": "original-emo_Relief-nl-0-seed1702-scale0.0", "bucket": "emo_Relief", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "7bd28128aab57c8989c7d0ab306a5184a78c0417a9193eb5852787f25d567f36", "task_id": "emo_Relief-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.03191152215003967, "target_z": -0.48437501868245597, "ce": 6.0305562019348145, "genuineness": 4.306513786315918, "identity": 0.6300172805786133, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/b629aa232077d0cf315c37cd.mp3" }, { "key": "original-emo_Relief-nl-0-seed1702-scale0.5", "bucket": "emo_Relief", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "265096e2144ee5bad4d94d528821267b8b4c3b6549c2334819befd85d0f71eb2", "task_id": "emo_Relief-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.07416731119155884, "target_z": -0.423828103982237, "ce": 5.95112943649292, "genuineness": 4.256305694580078, "identity": 0.7368499040603638, "hypothesis": "De deur staat nog open. Ik heb je jas op de stoel gelegd. Zeg maar wanneer je klaar bent.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/be9951167dd0cc3c01f0e5fd.mp3" }, { "key": "original-emo_Relief-nl-0-seed1702-scale0.75", "bucket": "emo_Relief", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "432d2740b25480c976e6be9bd5df623f9a1d037c6c6d53df02500a341c6e27b5", "task_id": "emo_Relief-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.11097070574760437, "target_z": -0.37109374399492484, "ce": 5.8875885009765625, "genuineness": 4.457139015197754, "identity": 0.5288803577423096, "hypothesis": "De deur staat nog open. Ik heb je jas op de Zotel Zotologolte setkomen lopen.", "wer": 0.42105263157894735, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/e89b2e50e2853c04e33439f3.mp3" }, { "key": "original-emo_Relief-nl-0-seed1702-scale1.0", "bucket": "emo_Relief", "language": "nl", "sentences": [ "De deur staat nog open.", "Ik heb je jas op de stoel gelegd.", "Zeg maar 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "dff1ddaa25b91ac6bbcfbd40eaa0e45681ef13d1233834451a9dc92c1d33432b", "task_id": "emo_Relief-nl-0", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.038726985454559326, "target_z": -0.474609367994079, "ce": 6.062326908111572, "genuineness": 4.20609712600708, "identity": 0.7631995677947998, "hypothesis": "De boor 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/audio/emo_Relief/nl/cbbeb38b7168dc64418a319b.mp3" }, { "key": "original-emo_Relief-nl-1-seed1701-scale0.0", "bucket": "emo_Relief", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "d2975085c3b714497583bff63295b245c865f22ec3e99c06f0274359807a6e6d", "task_id": "emo_Relief-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.19548222422599792, "target_z": -0.25, "ce": 6.022613525390625, "genuineness": 4.3881025314331055, "identity": 0.5645697116851807, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/0b0f43587706991f4da58e9e.mp3" }, { "key": "original-emo_Relief-nl-1-seed1701-scale0.5", "bucket": "emo_Relief", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "8d58d9e8ed917504e8e4dfb38327db792a2938eec4be5da591de6881539ee986", "task_id": "emo_Relief-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.07689347863197327, "target_z": -0.41992186932854014, "ce": 6.022613525390625, "genuineness": 4.2249250411987305, "identity": 0.46599578857421875, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/b9ee6e27bafdfe36541ebb36.mp3" }, { "key": "original-emo_Relief-nl-1-seed1701-scale0.75", "bucket": "emo_Relief", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "25d30a0cdb1606b4012060dabf8b2a254eaaa5182b5e91dcbb19dec2841372d3", "task_id": "emo_Relief-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.14368483424186707, "target_z": -0.32421875733953626, "ce": 6.141753673553467, "genuineness": 4.281409740447998, "identity": 0.7405749559402466, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/746e78fefb94098e4fffe99b.mp3" }, { "key": "original-emo_Relief-nl-1-seed1701-scale1.0", "bucket": "emo_Relief", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "3795dfcf9d01a0ae027c55632ed1066dd0e035a215b9288aba0e9efd5a1e7b7b", "task_id": "emo_Relief-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.14368483424186707, "target_z": -0.32421875733953626, "ce": 6.1020402908325195, "genuineness": 4.293961524963379, "identity": 0.6921846866607666, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/cd3d4530145476791a7c0bae.mp3" }, { "key": "original-emo_Relief-nl-1-seed1702-scale0.0", "bucket": "emo_Relief", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "a90235ebb9d13fced458e0abb17287c11ceec4af8d0f96666b5d6f97a9be3244", "task_id": "emo_Relief-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.19957149028778076, "target_z": -0.24414062666807643, "ce": 6.157639026641846, "genuineness": 4.406930446624756, "identity": 0.7490571737289429, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/9ffd5506681aced76844c947.mp3" }, { "key": "original-emo_Relief-nl-1-seed1702-scale0.5", "bucket": "emo_Relief", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "7baa18c3311e49f171b2c118ad662f01d22e48eac3f06b914b2f4d83eb4599f8", "task_id": "emo_Relief-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.181851327419281, "target_z": -0.2695312586739974, "ce": 6.141753673553467, "genuineness": 4.432034492492676, "identity": 0.7365500926971436, "hypothesis": "ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/a33d1bbb22309c9adc3ef405.mp3" }, { "key": "original-emo_Relief-nl-1-seed1702-scale0.75", "bucket": "emo_Relief", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "0f52ec06d10ce7113ce5a4b853a991fb38f200030fb3f49ed635a09cda1e3df1", "task_id": "emo_Relief-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.11505997180938721, "target_z": -0.3652343706630013, "ce": 6.078212261199951, "genuineness": 4.218649387359619, "identity": 0.6808675527572632, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/c409b498eeec5e2da4330fc2.mp3" }, { "key": "original-emo_Relief-nl-1-seed1702-scale1.0", "bucket": "emo_Relief", "language": "nl", "sentences": [ "Ik heb het kleine doosje gevonden.", "Het stond naast het oude raam.", "We 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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 Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.", "Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word." ], "seconds": 10.2, "frames": 128, "seeds": [ 1701, 1702 ], "scales": [ 0.0, 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": "0eedaf87e72e8eefb7fe44359540a31575a4eb2062d24fd11229a12fcab20a7f", "mp3_sha256": "adc3512249ca005629956eb40e5c321931701a3fbedd85854dca6be912434bff", "task_id": "emo_Relief-nl-1", "phase": "standard", "candidate": "standard", "neutral_prompt": "GENERAL: One adult speaker in a clean recording. Intense Relief. Make the requested delivery clearly audible, not merely implied by the words. Preserve every word.\nSCRIPT:\n(Intense Relief. 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 Relief. 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 Relief. 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": 0.1368694007396698, "target_z": -0.33398436532515674, "ce": 6.086154937744141, "genuineness": 4.344170093536377, "identity": 0.5497056245803833, "hypothesis": "Ik heb het kleine doosje gevonden. Het stond naast het oude raam. We kunnen er samen in kijken.", "wer": 0.0, "duration_error_s": 0.040000000000000924, "model_predictions_not_human_ratings": true }, "audio_url": "https://huggingface.co/datasets/laion/Humaneness-Voice-Large-1.5-Intense-Bucket-LoRAs-Demo-Audio/resolve/main/audio/emo_Relief/nl/c609802e99af364f92feae17.mp3" } ], "source_standard_audio_unchanged": true }